unsloth/pyproject.toml

1187 lines
97 KiB
TOML
Raw Permalink Normal View History

2023-11-29 16:51:54 +00:00
[build-system]
2025-10-19 01:11:58 +00:00
requires = ["setuptools==80.9.0", "setuptools-scm==9.2.0"]
2023-11-29 16:51:54 +00:00
build-backend = "setuptools.build_meta"
[project]
name = "unsloth"
2025-07-01 08:02:51 +00:00
dynamic = ["version"]
2025-10-08 03:50:31 +00:00
description = "2-5X faster training, reinforcement learning & finetuning"
2023-11-29 16:51:54 +00:00
readme = "README.md"
requires-python = ">=3.9,<3.15"
2025-10-08 03:50:31 +00:00
license = "Apache-2.0"
keywords = ["ai", "llm", "reinforcement learning", "machine learning", "artificial intelligence", "pytorch"]
2023-11-29 16:51:54 +00:00
authors = [
{email = "info@unsloth.ai"},
{name = "Unsloth AI team"},
2023-11-29 16:51:54 +00:00
]
maintainers = [
{name = "Daniel Han", email = "daniel@unsloth.ai"},
{name = "Michael Han", email = "info@unsloth.ai"},
2023-11-29 16:51:54 +00:00
]
classifiers = [
"Programming Language :: Python",
2025-10-08 03:50:31 +00:00
"Environment :: GPU",
"Environment :: GPU :: NVIDIA CUDA",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
2023-11-29 16:51:54 +00:00
]
dependencies = [
"typer",
"pydantic",
"pyyaml",
"nest-asyncio",
]
[project.scripts]
unsloth = "unsloth_cli:app"
2023-11-29 16:51:54 +00:00
2025-07-01 08:02:51 +00:00
[tool.setuptools.dynamic]
version = {attr = "unsloth.models._utils.__version__"}
2023-11-30 14:22:09 +00:00
[tool.setuptools]
include-package-data = true
[tool.setuptools.package-data]
Fix studio frontend build producing empty Tailwind CSS Two issues caused the studio frontend to render without any styling when installed via `pip install` (non-editable): 1. `pyproject.toml` package-data only included `frontend/dist/**/*`. The `include-package-data = true` setting relies on `git ls-files`, which fails in isolated builds (pip/uv copy source to a temp dir without `.git`). This meant `frontend/src/`, `package.json`, `vite.config.ts`, and other build files were missing from the installed package. Tailwind had no source files to scan. 2. Python venvs auto-create a `.gitignore` with a bare `*` pattern. Tailwind v4's oxide scanner walks parent directories and respects `.gitignore` -- so even when source files are present, the venv's `*` pattern causes the scanner to skip all `.tsx` files. The result is a 34KB CSS skeleton with zero utility classes instead of the expected 265KB. Additionally, Vite adds `crossorigin` to script/link tags by default. This forces CORS mode on font subresource loads, which Firefox HTTPS-Only Mode does not exempt -- causing all @font-face downloads to fail silently when Studio is served over HTTP. Changes: - pyproject.toml: Expand package-data to include frontend source, config files, setup scripts, and backend requirements using glob patterns (no node_modules) - studio/setup.sh: Temporarily hide parent .gitignore files containing a bare `*` during `npm run build`, with trap-based restoration - studio/backend/main.py: Strip `crossorigin` attributes from HTML at serve time so fonts load correctly on any protocol
2026-03-16 04:52:15 +00:00
studio = [
"*.sh",
"*.ps1",
"*.bat",
"frontend/dist/**/*",
"frontend/*.json",
"frontend/*.ts",
"frontend/*.js",
"frontend/*.html",
"frontend/*.yaml",
"frontend/.git*",
"backend/requirements/**/*",
"backend/core/data_recipe/oxc-validator/*.json",
"backend/core/data_recipe/oxc-validator/*.mjs",
]
2023-11-30 14:22:09 +00:00
[tool.setuptools.packages.find]
include = ["unsloth*", "unsloth_cli*", "studio", "studio.backend*"]
exclude = ["images*", "tests*", "*.node_modules", "*.node_modules.*"]
2023-11-30 14:22:09 +00:00
2025-07-01 08:02:51 +00:00
[project.optional-dependencies]
triton = [
2025-10-08 03:52:38 +00:00
"triton>=3.0.0 ; ('linux' in sys_platform)",
2025-10-08 03:50:31 +00:00
"triton-windows ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-07-01 08:02:51 +00:00
]
Fix transformers 4.57.1 (#3473) * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * custom_datatype * recheck * Float16 * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
2025-10-17 11:05:10 +00:00
huggingfacenotorch = [
2025-10-08 03:50:31 +00:00
"wheel>=0.42.0",
2025-07-01 08:02:51 +00:00
"packaging",
2025-10-08 03:50:31 +00:00
"numpy",
2025-07-01 08:02:51 +00:00
"tqdm",
"psutil",
2025-10-08 03:50:31 +00:00
"tyro",
"protobuf",
"sentencepiece>=0.2.0",
Formatting & bug fixes (#3563) * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning * fbgemm fp8 block quant support (>=1.4.0) (#3531) * fbgemm fp8 block quant support (>=1.4.0) * Verify for fp8 support before proceeding * Use unsloth zoo's Version and improve comments * spacessss * Update vision.py * Update vision.py * Update rl.py * vllm_sampling_params * Update rl.py * Update rl.py * Update rl.py * Add `ruff` pre-commit hook and apply it (#3424) * Add Ruff pre-commit config and workflow * Add kwarg spacing enforcement helper * Apply Ruff formatting * Update fp8.py * Revert ruff on some files * Update * force-exclude = true * Datasets issue * Ruff * Remove mapper * Update mapper.py * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> Co-authored-by: Dan Saunders <danjsaund@gmail.com>
2025-11-07 14:00:22 +00:00
"datasets>=3.4.1,!=4.0.*,!=4.1.0,<4.4.0",
2025-07-01 08:02:51 +00:00
"accelerate>=0.34.1",
2026-01-15 15:00:25 +00:00
"peft>=0.18.0,!=0.11.0",
2025-07-29 08:03:19 +00:00
"huggingface_hub>=0.34.0",
2025-07-01 08:02:51 +00:00
"hf_transfer",
2025-10-08 03:50:31 +00:00
"diffusers",
2026-04-02 18:59:37 +00:00
"transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1,!=4.57.0,!=4.57.4,!=4.57.5,!=5.0.0,!=5.1.0,<=5.5.0",
Bug fixes (#3546) * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
2025-11-03 14:47:26 +00:00
"trl>=0.18.2,!=0.19.0,<=0.24.0",
2026-01-27 15:17:45 +00:00
"sentence-transformers",
Fix transformers 4.57.1 (#3473) * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * custom_datatype * recheck * Float16 * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
2025-10-17 11:05:10 +00:00
]
huggingface = [
"unsloth[huggingfacenotorch]",
2026-04-16 19:06:10 +00:00
"unsloth_zoo>=2026.4.8",
Fix transformers 4.57.1 (#3473) * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * custom_datatype * recheck * Float16 * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
2025-10-17 11:05:10 +00:00
"torchvision",
2025-07-01 08:02:51 +00:00
"unsloth[triton]",
]
2025-10-08 03:50:31 +00:00
windows = [
2025-07-01 08:02:51 +00:00
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0 ; (sys_platform == 'win32')",
"xformers>=0.0.22.post7 ; (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
2025-08-07 10:29:44 +00:00
base = [
"unsloth[huggingface]",
]
2025-07-01 08:02:51 +00:00
cu118only = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.22.post7%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121only = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch211 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch211 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch212 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.23.post1%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch212 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.23.post1-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch220 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.24%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch220 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.24-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch230 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27%2Bcu118-cp312-cp312-manylinux2014_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch230 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.27-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.27-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.27-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.27-cp312-cp312-manylinux2014_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch240 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27.post2%2Bcu118-cp39-cp39-manylinux2014_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27.post2%2Bcu118-cp310-cp310-manylinux2014_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27.post2%2Bcu118-cp311-cp311-manylinux2014_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.27.post2%2Bcu118-cp312-cp312-manylinux2014_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch240 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post1-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post1-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post1-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post1-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu124onlytorch240 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post1-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch250 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.28.post2-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.28.post2-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.28.post2-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.28.post2-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch250 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post2-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post2-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post2-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.28.post2-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu124onlytorch250 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.28.post2-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch251 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post1-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post1-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post1-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post1-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu121onlytorch251 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.29.post1-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.29.post1-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.29.post1-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu121/xformers-0.0.29.post1-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu124onlytorch251 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post1-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch260 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post3-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post3-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post3-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.29.post3-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
cu124onlytorch260 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu124/xformers-0.0.29.post3-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu126onlytorch260 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.29.post3-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch270 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.30-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
]
2025-07-01 08:02:51 +00:00
cu126onlytorch270 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.30-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu128onlytorch270 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp39-cp39-manylinux_2_28_x86_64.whl ; python_version=='3.9' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp310-cp310-manylinux_2_28_x86_64.whl ; python_version=='3.10' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp311-cp311-manylinux_2_28_x86_64.whl ; python_version=='3.11' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp312-cp312-manylinux_2_28_x86_64.whl ; python_version=='3.12' and ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp39-cp39-win_amd64.whl ; python_version=='3.9' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp310-cp310-win_amd64.whl ; python_version=='3.10' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp311-cp311-win_amd64.whl ; python_version=='3.11' and (sys_platform == 'win32')",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.30-cp312-cp312-win_amd64.whl ; python_version=='3.12' and (sys_platform == 'win32')",
2025-07-01 08:02:51 +00:00
]
cu118onlytorch271 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.31.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu118/xformers-0.0.31.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu126onlytorch271 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.31.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.31.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu128onlytorch271 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.31.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.31.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu118onlytorch280 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.32.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.32.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu126onlytorch280 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.32.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.32.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu128onlytorch280 = [
2025-10-08 03:50:31 +00:00
"xformers @ https://download.pytorch.org/whl/cu129/xformers-0.0.32.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu129/xformers-0.0.32.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
2025-10-27 04:49:30 +00:00
cu130onlytorch280 = [
]
cu126onlytorch290 = [
2025-11-25 09:36:11 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.33.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.33.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
2025-10-27 04:49:30 +00:00
]
cu128onlytorch290 = [
2025-11-25 09:36:11 +00:00
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.33.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.33.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
2025-10-27 04:49:30 +00:00
]
cu130onlytorch290 = [
2025-11-25 09:36:11 +00:00
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.33.post1-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.33.post1-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu126onlytorch291 = [
2025-12-08 00:40:51 +00:00
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.33.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.33.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
2025-11-25 09:36:11 +00:00
]
cu128onlytorch291 = [
2025-12-08 00:40:51 +00:00
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.33.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.33.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
2025-11-25 09:36:11 +00:00
]
cu130onlytorch291 = [
2025-12-08 00:40:51 +00:00
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.33.post2-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.33.post2-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
2025-10-27 04:49:30 +00:00
]
cu126onlytorch2100 = [
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu126/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu128onlytorch2100 = [
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu128/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
cu130onlytorch2100 = [
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-manylinux_2_28_x86_64.whl ; ('linux' in sys_platform)",
"xformers @ https://download.pytorch.org/whl/cu130/xformers-0.0.34-cp39-abi3-win_amd64.whl ; (sys_platform == 'win32')",
]
2025-07-01 08:02:51 +00:00
cu118 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118only]",
]
cu121 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121only]",
]
cu118-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu118onlytorch211]",
]
cu121-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu121onlytorch211]",
]
cu118-torch212 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu118onlytorch212]",
]
cu121-torch212 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu121onlytorch212]",
]
cu118-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch220]",
]
cu121-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch220]",
]
cu118-torch230 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch230]",
]
cu121-torch230 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch230]",
]
cu118-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch240]",
]
cu121-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch240]",
]
cu124-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch240]",
]
cu118-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch250]",
]
cu121-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch250]",
]
cu124-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch250]",
]
cu118-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch251]",
]
cu121-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch251]",
]
cu124-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch251]",
]
cu118-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch260]",
]
cu124-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch260]",
]
cu126-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu126onlytorch260]",
]
cu118-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch270]",
]
2025-07-01 08:02:51 +00:00
cu126-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu126onlytorch270]",
]
cu128-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu128onlytorch270]",
]
cu118-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch271]",
]
cu126-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch271]",
]
cu128-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch271]",
]
cu118-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch280]",
]
cu126-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch280]",
]
cu128-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch280]",
]
2025-10-27 04:49:30 +00:00
cu130-torch280 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch280]",
]
cu126-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch290]",
]
cu128-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch290]",
]
cu130-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch290]",
]
2025-11-25 09:36:11 +00:00
cu126-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch291]",
]
cu128-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch291]",
]
cu130-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch291]",
]
cu126-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch2100]",
]
cu128-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch2100]",
]
cu130-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch2100]",
]
2025-07-01 08:02:51 +00:00
kaggle = [
"unsloth[huggingface]",
]
kaggle-new = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
]
conda = [
"unsloth[huggingface]",
]
colab-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu121onlytorch211]",
]
colab-ampere-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu121onlytorch211]",
"packaging",
"ninja",
2025-10-08 03:50:31 +00:00
"flash-attn>=2.6.3 ; ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
colab-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch220]",
]
colab-ampere-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch220]",
"packaging",
"ninja",
2025-10-08 03:50:31 +00:00
"flash-attn>=2.6.3 ; ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
colab-new = [
2026-04-16 19:06:10 +00:00
"unsloth_zoo>=2026.4.8",
2025-07-01 08:02:51 +00:00
"packaging",
"tyro",
2026-04-02 18:59:37 +00:00
"transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1,!=4.57.0,!=4.57.4,!=4.57.5,!=5.0.0,!=5.1.0,<=5.5.0",
Formatting & bug fixes (#3563) * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning * fbgemm fp8 block quant support (>=1.4.0) (#3531) * fbgemm fp8 block quant support (>=1.4.0) * Verify for fp8 support before proceeding * Use unsloth zoo's Version and improve comments * spacessss * Update vision.py * Update vision.py * Update rl.py * vllm_sampling_params * Update rl.py * Update rl.py * Update rl.py * Add `ruff` pre-commit hook and apply it (#3424) * Add Ruff pre-commit config and workflow * Add kwarg spacing enforcement helper * Apply Ruff formatting * Update fp8.py * Revert ruff on some files * Update * force-exclude = true * Datasets issue * Ruff * Remove mapper * Update mapper.py * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> Co-authored-by: Dan Saunders <danjsaund@gmail.com>
2025-11-07 14:00:22 +00:00
"datasets>=3.4.1,!=4.0.*,!=4.1.0,<4.4.0",
2025-07-01 08:02:51 +00:00
"sentencepiece>=0.2.0",
"tqdm",
"psutil",
"wheel>=0.42.0",
"numpy",
"protobuf",
2025-07-29 08:03:19 +00:00
"huggingface_hub>=0.34.0",
2025-07-01 08:02:51 +00:00
"hf_transfer",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[triton]",
2026-01-27 15:17:45 +00:00
"sentence-transformers",
2025-07-01 08:02:51 +00:00
]
colab-no-deps = [
"accelerate>=0.34.1",
Bug fixes (#3546) * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
2025-11-03 14:47:26 +00:00
"trl>=0.18.2,!=0.19.0,<=0.24.0",
2026-01-15 15:00:25 +00:00
"peft>=0.18.0",
2025-10-08 03:50:31 +00:00
"xformers ; ('linux' in sys_platform or sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"protobuf",
]
colab = [
"unsloth[cu121]",
]
flashattention = [
2025-10-08 03:50:31 +00:00
"packaging ; ('linux' in sys_platform)",
"ninja ; ('linux' in sys_platform)",
"flash-attn>=2.6.3 ; ('linux' in sys_platform)",
2025-07-01 08:02:51 +00:00
]
colab-ampere = [
"unsloth[colab-ampere-torch220]",
"unsloth[flashattention]",
]
cu118-ampere = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118only]",
"unsloth[flashattention]",
]
cu121-ampere = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121only]",
"unsloth[flashattention]",
]
cu118-ampere-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu118onlytorch211]",
"unsloth[flashattention]",
]
cu121-ampere-torch211 = [
"unsloth[huggingface]",
"bitsandbytes==0.45.5",
"unsloth[cu121onlytorch211]",
"unsloth[flashattention]",
]
cu118-ampere-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch220]",
"unsloth[flashattention]",
]
cu121-ampere-torch220 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch220]",
"unsloth[flashattention]",
]
cu118-ampere-torch230 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch230]",
"unsloth[flashattention]",
]
cu121-ampere-torch230 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch230]",
"unsloth[flashattention]",
]
cu118-ampere-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch240]",
"unsloth[flashattention]",
]
cu121-ampere-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch240]",
"unsloth[flashattention]",
]
cu124-ampere-torch240 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch240]",
"unsloth[flashattention]",
]
cu118-ampere-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch250]",
"unsloth[flashattention]",
]
cu121-ampere-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch250]",
"unsloth[flashattention]",
]
cu124-ampere-torch250 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch250]",
"unsloth[flashattention]",
]
cu118-ampere-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch251]",
"unsloth[flashattention]",
]
cu121-ampere-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu121onlytorch251]",
"unsloth[flashattention]",
]
cu124-ampere-torch251 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch251]",
"unsloth[flashattention]",
]
cu118-ampere-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu118onlytorch260]",
"unsloth[flashattention]",
]
cu124-ampere-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu124onlytorch260]",
"unsloth[flashattention]",
]
cu126-ampere-torch260 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu126onlytorch260]",
"unsloth[flashattention]",
]
cu118-ampere-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch270]",
"unsloth[flashattention]",
]
2025-07-01 08:02:51 +00:00
cu126-ampere-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu126onlytorch270]",
"unsloth[flashattention]",
]
cu128-ampere-torch270 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
2025-07-01 08:02:51 +00:00
"unsloth[cu128onlytorch270]",
"unsloth[flashattention]",
]
cu118-ampere-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch271]",
"unsloth[flashattention]",
]
cu126-ampere-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch271]",
"unsloth[flashattention]",
]
cu128-ampere-torch271 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch271]",
"unsloth[flashattention]",
]
cu118-ampere-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu118onlytorch280]",
"unsloth[flashattention]",
]
cu126-ampere-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch280]",
"unsloth[flashattention]",
]
cu128-ampere-torch280 = [
"unsloth[huggingface]",
2025-10-08 03:50:31 +00:00
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch280]",
"unsloth[flashattention]",
]
2025-10-27 04:49:30 +00:00
cu130-ampere-torch280 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch280]",
"unsloth[flashattention]",
]
cu126-ampere-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch290]",
]
cu128-ampere-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch290]",
]
cu130-ampere-torch290 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch290]",
]
2025-11-25 09:36:11 +00:00
cu126-ampere-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch291]",
]
cu128-ampere-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch291]",
]
cu130-ampere-torch291 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch291]",
]
cu126-ampere-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu126onlytorch2100]",
]
cu128-ampere-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu128onlytorch2100]",
]
cu130-ampere-torch2100 = [
"unsloth[huggingface]",
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
"unsloth[cu130onlytorch2100]",
]
2025-07-01 08:02:51 +00:00
flashattentiontorch260abiFALSEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
flashattentiontorch260abiTRUEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
flashattentiontorch250abiFALSEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
flashattentiontorch250abiTRUEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.5cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
flashattentiontorch240abiFALSEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiFALSE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
flashattentiontorch240abiTRUEcu12x = [
2025-10-08 03:50:31 +00:00
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp39-cp39-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.9'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp310-cp310-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.10'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp311-cp311-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.11'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp312-cp312-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.12'",
"flash-attn @ https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.4cxx11abiTRUE-cp313-cp313-linux_x86_64.whl ; ('linux' in sys_platform) and python_version == '3.13'",
2025-07-01 08:02:51 +00:00
]
2025-10-27 06:17:59 +00:00
intelgputorch260 = [
2025-10-27 04:59:51 +00:00
"unsloth_zoo[intelgpu]",
"unsloth[huggingfacenotorch]",
2025-07-01 08:02:51 +00:00
2025-10-08 03:50:31 +00:00
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.2.0-cp39-cp39-linux_x86_64.whl#sha256=147607f190a7d7aa24ba454def5977fbbfec792fdae18e4ed278cfec29b69271 ; ('linux' in sys_platform) and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.2.0-cp310-cp310-linux_x86_64.whl#sha256=23aa423fa1542afc34f67eb3ba8ef20060f6d1b3a4697eaeab22b11c92b30f2b ; ('linux' in sys_platform) and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.2.0-cp311-cp311-linux_x86_64.whl#sha256=bcfa995229bbfd9ffd8d6c8d9f6428d393e876fa6e23ee3c20e3c0d73ca75ca5 ; ('linux' in sys_platform) and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.2.0-cp312-cp312-linux_x86_64.whl#sha256=bd340903d03470708df3442438acb8b7e08087ab9e61fbe349b2872bf9257ab0 ; ('linux' in sys_platform) and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.2.0-cp313-cp313-linux_x86_64.whl#sha256=814dccc8a07159e6eca74bed70091bc8fea2d9dd87b0d91845f9f38cde62f01c ; ('linux' in sys_platform) and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-07-01 08:02:51 +00:00
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-10-08 03:50:31 +00:00
"torch @ https://download.pytorch.org/whl/xpu/torch-2.6.0%2Bxpu-cp39-cp39-linux_x86_64.whl#sha256=6a8adf6dc4c089406e8b3a7e58ab57a463bddf9b07130d2576e76eced43e92af ; ('linux' in sys_platform) and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.6.0%2Bxpu-cp310-cp310-linux_x86_64.whl#sha256=ff4561cbf07c83bbccaa0f6e9bb0e6dcf721bacd53c9c43c4eb0e7331b4792f9 ; ('linux' in sys_platform) and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.6.0%2Bxpu-cp311-cp311-linux_x86_64.whl#sha256=12005f66b810ddd3ab93f86c4522bcfdd412cbd27fc9d189b661ff7509bc5e8a ; ('linux' in sys_platform) and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.6.0%2Bxpu-cp312-cp312-linux_x86_64.whl#sha256=c4c5c67625cdacf35765c2b94e61fe166e3c3f4a14521b1212a59ad1b3eb0f2e ; ('linux' in sys_platform) and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.6.0%2Bxpu-cp313-cp313-linux_x86_64.whl#sha256=e6864f7a60a5ecc43d5d38f59a16e5dd132384f73dfd3a697f74944026038f7b ; ('linux' in sys_platform) and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-07-01 08:02:51 +00:00
]
2025-10-27 06:17:59 +00:00
intel-gpu-torch260 = [
"unsloth[intelgputorch260]"
]
intelgputorch270 = [
2025-10-27 04:59:51 +00:00
"unsloth_zoo[intelgpu]",
"unsloth[huggingfacenotorch]",
2025-07-01 08:02:51 +00:00
2025-10-08 03:50:31 +00:00
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=749a7098492c6a27b356c97149a4a62973b953eae60bc1b6259260974f344913 ; ('linux' in sys_platform) and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=44362e80abd752471a08341093321955b066daa2cfb4810e73b8e3b240850f93 ; ('linux' in sys_platform) and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=faa6b8c945a837a080f641bc8ccc77a98fa66980dcd7e62e715fd853737343fd ; ('linux' in sys_platform) and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=40f6fb65b345dc9a61813abe7ac9a585f2c9808f414d140cc2a5f11f53ee063c ; ('linux' in sys_platform) and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=b22b4c02ec71b4bfc862ae3cdfd2871dc0b05d2b1802f5db2196e0f897d581e9 ; ('linux' in sys_platform) and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp39-cp39-win_amd64.whl#sha256=d4b738d7fa5100c1bd766f91614962828a4810eb57b4df92cd5214a83505a752 ; sys_platform == 'win32' and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp310-cp310-win_amd64.whl#sha256=143fe8a64d807bcdb7d81bbc062816add325570aa160448454ab6ded4a0a17a1 ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp311-cp311-win_amd64.whl#sha256=a8025459ff325d6e3532eb5cf72519db1b178155e7d60aff6c56beb5968fc758 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp312-cp312-win_amd64.whl#sha256=0dd07e6d5b872e42e48f5ee140e609d4554ca3cc509d5bf509ac232267cf358e ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.3.0-cp313-cp313-win_amd64.whl#sha256=a936a18182d8e065a9933afc9a3ebbffadd38604969f87c493831214539fc027 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-07-01 08:02:51 +00:00
2025-10-08 03:50:31 +00:00
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp39-cp39-linux_x86_64.whl#sha256=f8ee75e50fcbb37ed5b498299ca2264da99ab278a93fae2358e921e4a6e28273 ; ('linux' in sys_platform) and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp310-cp310-linux_x86_64.whl#sha256=d6fdc342961d98fdcd9d03dfd491a3208bb5f7fbb435841f8f72ce9fdcd2d026 ; ('linux' in sys_platform) and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp311-cp311-linux_x86_64.whl#sha256=74d07f9357df5cf2bf223ad3c84de16346bfaa0504f988fdd5590d3e177e5e86 ; ('linux' in sys_platform) and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp312-cp312-linux_x86_64.whl#sha256=c806d44aa2ca5d225629f6fbc6c994d5deaac2d2cde449195bc8e3522ddd219a ; ('linux' in sys_platform) and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp313-cp313-linux_x86_64.whl#sha256=25d8277b7f01d42e2e014ccbab57a2692b6ec4eff8dcf894eda1b297407cf97a ; ('linux' in sys_platform) and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp39-cp39-win_amd64.whl#sha256=046e85125266ae69c1a0d083e6c092f947ab4b6b41532c16bafe40dbced845df ; sys_platform == 'win32' and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=9ebaeffb82b0b3e39b6030927d3ebe0eb62a0e9045a3b2d7b0a9e7b15222c0db ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=356ba66cee127e7e2c942880bd50e03768306a4ea08d358a0f29c6eebfc4bc81 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=94739e665d9b4d5cd7af5f517cb6103f6f9fb421c095184609653a24524040f5 ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=31df3cb674918e89bc8c532baa331dc84f4430e1f9c0ec379232db44cba78355 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-07-01 08:02:51 +00:00
]
2025-10-27 06:17:59 +00:00
intel-gpu-torch270 = [
"unsloth[intelgputorch270]"
]
intelgputorch280 = [
2025-10-27 04:59:51 +00:00
"unsloth_zoo[intelgpu]",
"unsloth[huggingfacenotorch]",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=ac4d8e33986b1c3c5e48151640539272b2187e83016985853111b46fb82c3c94 ; 'linux' in sys_platform and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=999fef4c1f711092b9d3086525920545df490de476ecebe899ffc777019ae17f ; 'linux' in sys_platform and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=57b09c8c492985ff6a27cd3a22b08e8f7b96b407bd8030967b6efbb9f63b80cf ; 'linux' in sys_platform and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=df4bb3282bac9a3b90231700077110d8680b338416de03c2b7c6133c9b602649 ; 'linux' in sys_platform and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=60da63c99ca827bdcb0df28e0298bf7d066dc607454c6d6176783cb4e79d838b ; 'linux' in sys_platform and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp39-cp39-win_amd64.whl#sha256=64aea8de349f3e2e0ebf4c24b011a8122531fdffda5776edaef45829cc241cf8 ; sys_platform == 'win32' and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp310-cp310-win_amd64.whl#sha256=ae573d255b257fdbed319a3440dc9d0a721e31160ab7f6eba1b2226e6a409a1d ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp311-cp311-win_amd64.whl#sha256=8e0ea4558e5776d8ddab0264310be9b26aee5641bcac0da023537556d4317b86 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp312-cp312-win_amd64.whl#sha256=4090dde07a4fffc34aaf855701a9db28e9fccb57b368ade520f1a0f8e811c878 ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.4.0-cp313-cp313-win_amd64.whl#sha256=a33d0888f3c8df028a2d028842715837d0049524d6c06b9bb11869890a13601a ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp39-cp39-linux_x86_64.whl ; 'linux' in sys_platform and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp310-cp310-linux_x86_64.whl ; 'linux' in sys_platform and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp311-cp311-linux_x86_64.whl ; 'linux' in sys_platform and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp312-cp312-linux_x86_64.whl ; 'linux' in sys_platform and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp313-cp313-linux_x86_64.whl ; 'linux' in sys_platform and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp39-cp39-win_amd64.whl#sha256=f2f401276892428e4875cf1d8717c5cbab704b16fc594ccf23795e7b16549a99 ; sys_platform == 'win32' and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=125c60cd59d51b39581a7e9afcd4679bc3a6b8c1f9440b1bb502a23fdd60571e ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=47f1a57258cd460e80b38b2ed6744e31587ab77a96b4215bf59546cb4bab5cc0 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=0937d8943c145a83d9bafc6f80ef28971167817f9eda26066d33f72caf8a6646 ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.8.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=e034aab1d71760dc80a731531be43673ffe15e99033b82d24e40d2e6d41bd8bf ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp39-cp39-manylinux_2_28_x86_64.whl#sha256=6e981c192045fc249c008441179ff237bb00174d818b875b0475730b63f0eaca ; 'linux' in sys_platform and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp310-cp310-manylinux_2_28_x86_64.whl#sha256=e5ba4805969277175ebfd59cc717093528cc6e3ada89ac2725fc7a3c1fee6169 ; 'linux' in sys_platform and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp311-cp311-manylinux_2_28_x86_64.whl#sha256=74c39c144104416bc4c5ad8c26ab0c169dc5cc6be58059e01bc3665dd0ef676f ; 'linux' in sys_platform and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp312-cp312-manylinux_2_28_x86_64.whl#sha256=0acec355b80c3899841184084f365df336c508602812e34a44007b8b60d53af4 ; 'linux' in sys_platform and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp313-cp313-manylinux_2_28_x86_64.whl#sha256=e2109ae773dad27b98ca17681044b4f876563c37f2382b75de3a371399edcff8 ; 'linux' in sys_platform and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp39-cp39-win_amd64.whl#sha256=5f7904e7048d414379bc8c1167260f1e84204f105db2d0a2f9c89e87ce1cf205 ; sys_platform == 'win32' and python_version == '3.9' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=005fca5e658ca8e37adb63c1a021c84f5e56dfa6cf0d601d89cfe40b9473f79f ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=c6d030f5361461550c0ff1339b5bca8585fc1e84fda2e64b6184e65a581e4f98 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=91aafd61864cdce27461cbec13ddbf28c1bc6494265a1e4b80131c64a3b7d18f ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.23.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=71dc4a6421742ed1e7f585b04a100ad53615c341fbccfbc255aefb38ea9091da ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
2025-10-27 06:17:59 +00:00
intel-gpu-torch280 = [
"unsloth[intelgputorch280]"
]
intelgputorch290 = [
"unsloth_zoo[intelgpu]",
"unsloth[huggingfacenotorch]",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=c169a1de14c19673b17c751290d467fa282fc90fa5da4314b2e5cdab1f553146 ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=013d9dd5d6479bd22983161f462e61c8dbe1d82e6730624a7a8d5945507eaa61 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=afc8cabfbf7ed51fd278d1e0f88d6afc157b0201bad4b99d681e4d542f9e66d4 ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=0d24c1716088f2764d0d24c64227732195b6a42706c3c5fc89eeb4904bfa0818 ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp310-cp310-win_amd64.whl#sha256=c83ab007311d9cfb6e809ee5a4587d99a9eef4be720b90da4f1aaa68b45139a0 ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp311-cp311-win_amd64.whl#sha256=debf75348da8e8c7166b4d4a9b91d1508bb8d6581e339f79f7604b2e6746bacd ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp312-cp312-win_amd64.whl#sha256=97337a47425f1963a723475bd61037460e84ba01db4f87a1d662c3718ff6c47e ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp313-cp313-win_amd64.whl#sha256=2caf8138695f6abb023ecd02031a2611ba1bf8fff2f19802567cb2fadefe9e87 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp310-cp310-linux_x86_64.whl#sha256=5afbe860ce991825a36b75706a523601087e414b77598ef0d9d3d565741c277d ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp311-cp311-linux_x86_64.whl#sha256=607fe419c32d6e8e0556f745742e7cff1d0babce51f54be890e0c1422359c442 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp312-cp312-linux_x86_64.whl#sha256=376bae584d89980b8e59934d248c38d5fa3b7d4687a4df1a19f4bc1d23dcc8c1 ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp313-cp313-linux_x86_64.whl#sha256=98d6a06dd7fb185874367b18bd609f05f16fdce4142a5980ca94461949965cd2 ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=47cc68f631f65bd9c84924d052cd04dec7531023caa85e80345e9c94611c887d ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=d56c44ab4818aba57e5c7b628f422d014e0d507427170a771c5be85e308b0bc6 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=18cad93aaff76a01ce73aef6935ece7cfc03344b905592ec731446c44d44592b ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.9.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=579929cdc10a76800ead41289cac191ea36d1b16f5f501d3fc25607d4375cd83 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp310-cp310-manylinux_2_28_x86_64.whl#sha256=cbfae2b79b7549fd368c2462fc8e94f8f26cc450782ee72138e908077c09a519 ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp311-cp311-manylinux_2_28_x86_64.whl#sha256=044fa36ef4b6b43edcd490b75c853fa4b3eb033c2bded29f8fbcf27734713c67 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp312-cp312-manylinux_2_28_x86_64.whl#sha256=4b91e4bec1d740a6211f02578a79888550b73f3a4e1383035f8f6d72f587212c ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp313-cp313-manylinux_2_28_x86_64.whl#sha256=88239e73ca37254bec84f29cd5887e10ff712de7edbbda3fbb3609cd6190d99e ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=19c7da8ca767d593e13a88a12bb08d06e34a673f6f26c2f9c191d60e81c02953 ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=9bb0d1421c544ac8e2eca5b47daacaf54706dc9139c003aa5e77ee5f355c5931 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=6a5194bc736089606342d48a3f6822829b167617e9495d91d753dd1bd46fda18 ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.24.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=da47a3ce2bb7f0301a31124668b5908f9b9e92d6241443de15a310ef9632fd83 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
2025-10-27 06:17:59 +00:00
intel-gpu-torch290 = [
"unsloth[intelgputorch290]"
]
intelgputorch210 = [
"unsloth_zoo[intelgpu]",
"unsloth[huggingfacenotorch]",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=c169a1de14c19673b17c751290d467fa282fc90fa5da4314b2e5cdab1f553146 ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=013d9dd5d6479bd22983161f462e61c8dbe1d82e6730624a7a8d5945507eaa61 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=afc8cabfbf7ed51fd278d1e0f88d6afc157b0201bad4b99d681e4d542f9e66d4 ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl#sha256=0d24c1716088f2764d0d24c64227732195b6a42706c3c5fc89eeb4904bfa0818 ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp310-cp310-win_amd64.whl#sha256=c83ab007311d9cfb6e809ee5a4587d99a9eef4be720b90da4f1aaa68b45139a0 ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp311-cp311-win_amd64.whl#sha256=debf75348da8e8c7166b4d4a9b91d1508bb8d6581e339f79f7604b2e6746bacd ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp312-cp312-win_amd64.whl#sha256=97337a47425f1963a723475bd61037460e84ba01db4f87a1d662c3718ff6c47e ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"pytorch_triton_xpu @ https://download.pytorch.org/whl/pytorch_triton_xpu-3.5.0-cp313-cp313-win_amd64.whl#sha256=2caf8138695f6abb023ecd02031a2611ba1bf8fff2f19802567cb2fadefe9e87 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp310-cp310-linux_x86_64.whl#sha256=abb1d1ec1ac672bac0ff35420c965f2df0c636ef9d94e2a830e34578489d0a57 ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp311-cp311-linux_x86_64.whl#sha256=71ad2f82da0f41eaec159f39fc85854e27c2391efa91b373e550648a6f4aaad3 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp312-cp312-linux_x86_64.whl#sha256=b473571d478912f92881cc13f15fa18f8463fb0fb8a068c96ed47a7d45a4da0a ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp313-cp313-linux_x86_64.whl#sha256=3bc64a746ff25a93de140902c60c9e819d7413f5cea1e88d80999c27a5901e9c ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=ce50691ab3fb6301d9b7bb8b3834cf5fa7152a2b5f91fd24c5efdc601a25b780 ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=cb9d37f21cb9fb7df67d62863f021c3144e8d8832b9ea8e8523ac308bc620ea1 ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=3ad605be4728b6d3a28a44d07dd794b1a9e45551b0057815bf25eb2a6d6a56a7 ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torch @ https://download.pytorch.org/whl/xpu/torch-2.10.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=2b4b56dd6c792aef82006904fa888692e3782e4ae5da27526801bad4898f05a5 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp310-cp310-manylinux_2_28_x86_64.whl#sha256=7e1e7b170fcf7161c8499b67156c5a05462243626dc0974010791a0bab4378d3 ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp311-cp311-manylinux_2_28_x86_64.whl#sha256=bd6add201bd7628af70437292e1447abb368e0b5f4ff9abd334ae435efd44792 ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp312-cp312-manylinux_2_28_x86_64.whl#sha256=6ad2543496bc29e59d3dd614a94d09aa9870318aedb66045344fffddfedd2cf8 ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp313-cp313-manylinux_2_28_x86_64.whl#sha256=80269f37865fcd8b57f20e4786efae2200bfa2b2727926c3c7acc82f0e7d3548 ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp310-cp310-win_amd64.whl#sha256=6b9485ba85dcba4d196d6134d9c3332fb228fb2556416bf0450a64e8a472fcba ; sys_platform == 'win32' and python_version == '3.10' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp311-cp311-win_amd64.whl#sha256=36cbaedf10f6412af5c89afd9aeea474e6a56a0050348ada8fabe1ecaf6b879e ; sys_platform == 'win32' and python_version == '3.11' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp312-cp312-win_amd64.whl#sha256=738357d97468d75fe3d510ac37e65130f2787f81d9bbc1518898f7396dc3403f ; sys_platform == 'win32' and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"torchvision @ https://download.pytorch.org/whl/xpu/torchvision-0.25.0%2Bxpu-cp313-cp313-win_amd64.whl#sha256=1c4b44b36a557f7381e3076fb8843366742238648441d607c8d049c6da0f8886 ; sys_platform == 'win32' and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
]
intel-gpu-torch210 = [
"unsloth[intelgputorch210]"
]
2025-10-27 06:17:59 +00:00
intel = [
"unsloth[intelgputorch280]",
]
2025-10-27 04:49:30 +00:00
amd = [
"unsloth[huggingfacenotorch]",
"bitsandbytes>=0.49.1 ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64' or platform_machine == 'aarch64')",
"bitsandbytes>=0.49.1 ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
2025-10-27 04:49:30 +00:00
]
2026-03-18 14:26:40 +00:00
rocm702-torch280 = [
"unsloth[amd]",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/triton-3.4.0%2Brocm7.0.2.gitf9e5bf54-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/triton-3.4.0%2Brocm7.0.2.gitf9e5bf54-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/triton-3.4.0%2Brocm7.0.2.gitf9e5bf54-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torch-2.8.0%2Brocm7.0.2.lw.git245bf6ed-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torch-2.8.0%2Brocm7.0.2.lw.git245bf6ed-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torch-2.8.0%2Brocm7.0.2.lw.git245bf6ed-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torchvision-0.23.0%2Brocm7.0.2.git824e8c87-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torchvision-0.23.0%2Brocm7.0.2.git824e8c87-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.0.2/torchvision-0.23.0%2Brocm7.0.2.git824e8c87-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
]
rocm72-torch291 = [
"unsloth[amd]",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.5.1%2Brocm7.2.0.gita272dfa8-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.5.1%2Brocm7.2.0.gita272dfa8-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.5.1%2Brocm7.2.0.gita272dfa8-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.5.1%2Brocm7.2.0.gita272dfa8-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.9.1%2Brocm7.2.0.lw.git7e1940d4-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.9.1%2Brocm7.2.0.lw.git7e1940d4-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.9.1%2Brocm7.2.0.lw.git7e1940d4-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.9.1%2Brocm7.2.0.lw.git7e1940d4-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/windows/rocm-rel-7.2/torch-2.9.1%2Brocmsdk20260116-cp312-cp312-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.12'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.24.0%2Brocm7.2.0.gitb919bd0c-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.24.0%2Brocm7.2.0.gitb919bd0c-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.24.0%2Brocm7.2.0.gitb919bd0c-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.24.0%2Brocm7.2.0.gitb919bd0c-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/windows/rocm-rel-7.2/torchvision-0.24.1%2Brocmsdk20260116-cp312-cp312-win_amd64.whl ; sys_platform == 'win32' and python_version == '3.12'",
]
rocm711-torch291 = [
"unsloth[amd]",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.5.1%2Brocm7.1.1.gita272dfa8-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.5.1%2Brocm7.1.1.gita272dfa8-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.5.1%2Brocm7.1.1.gita272dfa8-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.5.1%2Brocm7.1.1.gita272dfa8-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.9.1%2Brocm7.1.1.lw.git351ff442-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.9.1%2Brocm7.1.1.lw.git351ff442-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.9.1%2Brocm7.1.1.lw.git351ff442-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.9.1%2Brocm7.1.1.lw.git351ff442-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.24.0%2Brocm7.1.1.gitb919bd0c-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.24.0%2Brocm7.1.1.gitb919bd0c-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.24.0%2Brocm7.1.1.gitb919bd0c-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.24.0%2Brocm7.1.1.gitb919bd0c-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
]
rocm72-torch2100 = [
"unsloth[amd]",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.6.0%2Brocm7.2.0.gitba5c1517-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.6.0%2Brocm7.2.0.gitba5c1517-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.6.0%2Brocm7.2.0.gitba5c1517-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/triton-3.6.0%2Brocm7.2.0.gitba5c1517-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.10.0%2Brocm7.2.0.lw.gitb6ee5fde-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.10.0%2Brocm7.2.0.lw.gitb6ee5fde-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.10.0%2Brocm7.2.0.lw.gitb6ee5fde-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torch-2.10.0%2Brocm7.2.0.lw.gitb6ee5fde-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.25.0%2Brocm7.2.0.git82df5f59-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.25.0%2Brocm7.2.0.git82df5f59-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.25.0%2Brocm7.2.0.git82df5f59-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.2/torchvision-0.25.0%2Brocm7.2.0.git82df5f59-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
]
rocm711-torch2100 = [
"unsloth[amd]",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.6.0%2Brocm7.1.1.gitba5c1517-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.6.0%2Brocm7.1.1.gitba5c1517-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.6.0%2Brocm7.1.1.gitba5c1517-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"triton @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/triton-3.6.0%2Brocm7.1.1.gitba5c1517-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.10.0%2Brocm7.1.1.lw.gitd9556b05-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.10.0%2Brocm7.1.1.lw.gitd9556b05-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.10.0%2Brocm7.1.1.lw.gitd9556b05-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torch @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torch-2.10.0%2Brocm7.1.1.lw.gitd9556b05-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.25.0%2Brocm7.1.1.git82df5f59-cp310-cp310-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.10' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.25.0%2Brocm7.1.1.git82df5f59-cp311-cp311-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.11' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.25.0%2Brocm7.1.1.git82df5f59-cp312-cp312-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.12' and platform_machine == 'x86_64'",
"torchvision @ https://repo.radeon.com/rocm/manylinux/rocm-rel-7.1.1/torchvision-0.25.0%2Brocm7.1.1.git82df5f59-cp313-cp313-linux_x86_64.whl ; platform_system == 'Linux' and python_version == '3.13' and platform_machine == 'x86_64'",
]
2023-11-29 16:51:54 +00:00
[project.urls]
Fix tool call parsing, add tool outputs panel and UI improvements (#4416) * Add elapsed timer to tool status pill in Studio Show a count-up seconds timer (0s, 1s, 2s, ...) next to the tool status text in the composer area. Helps users gauge how long a tool call (web search, code execution) has been running. Timer resets when a new tool starts and disappears when all tools finish. * Fix tool call parsing, add tool outputs panel and reasoning copy button Backend: - Rewrite tool call XML parser to use balanced-brace JSON extraction instead of greedy regex, fixing truncation on nested braces in code/JSON arguments - Handle optional closing tags (</tool_call>, </function>, </parameter>) that models frequently omit - Support bare <function=...> tags without <tool_call> wrapper - Strip tool call markup from streamed content so raw XML never leaks into the chat UI - Use a persistent ~/studio_sandbox/ working directory for tool execution so files persist across calls within a session - Emit tool_start/tool_end SSE events so the frontend can display tool inputs and outputs Frontend: - Add collapsible "Tool Outputs" panel below assistant messages showing each tool call's input and output with copy buttons - Add copy button to reasoning blocks - Add elapsed timer to tool status pill - Update project URLs in pyproject.toml (http -> https, add docs link) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add interactive HTML preview with fullscreen toggle for code blocks HTML code fences now render an interactive sandboxed iframe preview below the syntax-highlighted code, similar to how SVG fences show an image preview. The iframe uses sandbox="allow-scripts" to allow JavaScript execution while blocking access to the parent page. Includes a fullscreen toggle (enlarge/minimize button) that expands the preview into a viewport overlay, dismissible via button, Escape key, or backdrop click. A streaming placeholder prevents partial HTML from rendering mid-stream. * Add tool call settings: auto-heal toggle, max iterations, timeout Add three user-configurable tool call settings to the Studio Settings panel: - Auto Heal Tool Calls: toggle to control fallback XML parsing of malformed tool calls from model output (default: on) - Max Tool Calls Per Message: slider 0-40 + Max to cap tool call iterations per message (default: 10) - Max Tool Call Duration: slider 1-30 minutes + Max to set per-tool-call execution timeout (default: 5 minutes) All settings persist to localStorage and flow through the full stack: frontend store -> API request -> Pydantic model -> route -> llama_cpp -> tools. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix tool call timeout: respect no-limit and apply to web search - Use a sentinel to distinguish timeout=None (no limit) from the default (300s). Previously None was silently replaced with _EXEC_TIMEOUT. - Pass the configured timeout to DDGS() for web searches so the setting applies uniformly to all tool types. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add input validation bounds and per-thread sandbox isolation - Add ge=0 constraint to max_tool_calls_per_message (rejects negative values) - Add ge=1 constraint to tool_call_timeout (minimum 1 second) - Thread session_id from frontend through backend to tool execution - Scope sandbox directories per conversation: ~/studio_sandbox/{thread_id}/ - Backwards compatible: API callers without session_id use ~/studio_sandbox/ * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix non-monotonic streaming and Python temp script path - Split tool markup stripping into closed-only (mid-stream) and full (final flush) to prevent cumulative text from shrinking mid-stream - Enforce monotonicity: only emit when cleaned text grows, so the proxy's delta logic (cumulative[len(prev_text):]) never breaks - Place Python temp scripts in the sandbox workdir instead of /tmp so sys.path[0] points to the sandbox and cross-call imports work * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Sanitize session_id to prevent path traversal in sandbox Strip path separators and parent-dir references from session_id before using it as a directory name. Verify the resolved path stays under ~/studio_sandbox/ as a second guard. * feat(chat): proper assistant-ui tool call UIs with sources Replace custom metadata-based ToolOutputsGroup with native assistant-ui tool-call content parts. Backend SSE tool_start/tool_end events now emit proper { type: "tool-call" } parts from the adapter, enabling per-tool UIs registered via tools.by_name in MessagePrimitive.Parts. - Web search: Globe icon, Source badges with favicons, auto-collapse when LLM starts responding - Python: Code icon, syntax-highlighted code via Streamdown/shiki, output block with copy - Terminal: Terminal icon, command in trigger, output with copy - ToolGroup wraps consecutive tool calls (skips for single calls) - Sources component renders URL badges at end of message - Flattened code block CSS (single border, no nested boxes) * fix(inference): respect empty enabled_tools allowlist `if payload.enabled_tools:` is falsy for [], falling through to ALL_TOOLS. Use `is not None` so an explicit empty list disables all tools as intended. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Shine1i <wasimysdev@gmail.com>
2026-03-18 15:28:02 +00:00
homepage = "https://unsloth.ai"
documentation = "https://unsloth.ai/docs"
repository = "https://github.com/unslothai/unsloth"
Formatting & bug fixes (#3563) * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit 4021da634ac2f4fa71441c209b2c0b8aa6c56583. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning * fbgemm fp8 block quant support (>=1.4.0) (#3531) * fbgemm fp8 block quant support (>=1.4.0) * Verify for fp8 support before proceeding * Use unsloth zoo's Version and improve comments * spacessss * Update vision.py * Update vision.py * Update rl.py * vllm_sampling_params * Update rl.py * Update rl.py * Update rl.py * Add `ruff` pre-commit hook and apply it (#3424) * Add Ruff pre-commit config and workflow * Add kwarg spacing enforcement helper * Apply Ruff formatting * Update fp8.py * Revert ruff on some files * Update * force-exclude = true * Datasets issue * Ruff * Remove mapper * Update mapper.py * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> Co-authored-by: Dan Saunders <danjsaund@gmail.com>
2025-11-07 14:00:22 +00:00
[tool.ruff]
target-version = "py311"
force-exclude = true
extend-exclude = [
"*chat_templates.py",
"*ollama_template_mappers.py",
"*_auto_install.py",
"*mapper.py",
]
[tool.ruff.lint]
select = ["E9", "F63", "F7", "F82"]
ignore = [
"E402",
"E722",
"F403",
"F405",
"F811",
"F821",
"F841",
"F401",
"E731",
"E741",
"F601",
"E712",
]
[tool.ruff.format]