mirror of
https://github.com/unslothai/unsloth
synced 2026-04-21 21:47:51 +00:00
* Allow Windows setup to complete without NVIDIA GPU setup.ps1 previously hard-exited if nvidia-smi was not found, blocking setup entirely on CPU-only or non-NVIDIA machines. The backend already supports CPU and MLX (Apple Silicon) in chat-only GGUF mode, and the Linux/Mac setup.sh handles missing GPUs gracefully. Changes: - Convert the GPU check from a hard exit to a warning - Guard CUDA toolkit installation behind $HasNvidiaSmi - Install CPU-only PyTorch when no GPU is detected - Build llama.cpp without CUDA flags when no GPU is present - Update doc comment to reflect CPU support * Cache frontend build across setup runs Skip the frontend npm install + build if frontend/dist already exists. Previously setup.ps1 nuked node_modules and package-lock.json on every run, and both scripts always rebuilt even when dist/ was already present. On a git clone editable install, the first setup run still builds the frontend as before. Subsequent runs skip it, saving several minutes. To force a rebuild, delete frontend/dist and re-run setup. * Show pip progress for PyTorch download on Windows The torch CUDA wheel is ~2.8 GB and the CPU wheel is ~300 MB. With | Out-Null suppressing all output, the install appeared completely frozen with no feedback. Remove | Out-Null for the torch install lines so pip's download progress bar is visible. Add a size hint so users know the download is expected to take a while. Also moves the Triton success message inside the GPU branch so it only prints when Triton was actually installed. * Guard CUDA env re-sanitization behind GPU check in llama.cpp build The CUDA_PATH re-sanitization block (lines 1020-1033) references $CudaToolkitRoot which is only set when $HasNvidiaSmi is true and the CUDA Toolkit section runs. On CPU-only machines, $CudaToolkitRoot is null, causing Split-Path to throw: Split-Path : Cannot bind argument to parameter 'Path' because it is null. Wrap the entire block in `if ($HasNvidiaSmi -and $CudaToolkitRoot)`. * Rebuild frontend when source files are newer than dist/ Instead of only checking if dist/ exists, compare source file timestamps against the dist/ directory. If any file in frontend/src/ is newer than dist/, trigger a rebuild. This handles the case where a developer pulls new frontend changes and re-runs setup -- stale assets get rebuilt automatically. * Fix cmake not found on Windows after winget install Two issues fixed: 1. After winget installs cmake, Refresh-Environment may not pick up the new PATH entry (MSI PATH changes sometimes need a new shell). Added a fallback that probes cmake's default install locations (Program Files, LocalAppData) and adds the directory to PATH explicitly if found. 2. If cmake is still unavailable when the llama.cpp build starts (e.g. winget failed silently or PATH was not updated), the build now skips gracefully with a [SKIP] warning instead of crashing with "cmake : The term 'cmake' is not recognized". * Fix frontend rebuild detection and decouple oxc-validator install Address review feedback: - Check entire frontend/ directory for changes, not just src/. The build also depends on package.json, vite.config.ts, tailwind.config.ts, public/, and other config files. A change to any of these now triggers a rebuild. - Move oxc-validator npm install outside the frontend build gate in setup.sh so it always runs on setup, matching setup.ps1 which already had it outside the gate. * Show cmake errors on failure and retry CUDA VS integration with elevation Two fixes for issue #4405 (Windows setup fails at cmake configure): 1. cmake configure: capture output and display it on failure instead of piping to Out-Null. When the error mentions "No CUDA toolset found", print a hint about the CUDA VS integration files. 2. CUDA VS integration copy: when the direct Copy-Item fails (needs admin access to write to Program Files), retry with Start-Process -Verb RunAs to prompt for elevation. This is the root cause of the "No CUDA toolset found" cmake failure -- the .targets files that let MSBuild compile .cu files are missing from the VS BuildCustomizations directory. * Address reviewer feedback: cmake PATH persistence, stale cache, torch error check 1. Persist cmake PATH to user registry so Refresh-Environment cannot drop it later in the same setup run. Previously the process-only PATH addition at phase 1 could vanish when Refresh-Environment rebuilt PATH from registry during phase 2/3 installs. 2. Clean stale CMake cache before configure. If a previous run built with CUDA and the user reruns without a GPU (or vice versa), the cached GGML_CUDA value would persist. Now the build dir is removed before configure. 3. Explicitly set -DGGML_CUDA=OFF for CPU-only builds instead of just omitting CUDA flags. This prevents cmake from auto-detecting a partial CUDA installation. 4. Fix CUDA cmake flag indentation -- was misaligned from the original PR, now consistently indented inside the if/else block. 5. Fail hard if pip install torch returns a non-zero exit code instead of silently continuing with a broken environment. * Remove extra CUDA cmake flags to align Windows with Linux build Drop GGML_CUDA_FA_ALL_QUANTS, GGML_CUDA_F16, GGML_CUDA_GRAPHS, GGML_CUDA_FORCE_CUBLAS, and GGML_CUDA_PEER_MAX_BATCH_SIZE flags. The Linux build in setup.sh only sets GGML_CUDA=ON and lets llama.cpp use its defaults for everything else. Keep Windows consistent. * Address reviewer round 2: GPU probe fallback, Triton check, stale binary rebuild 1. GPU detection: fallback to default nvidia-smi install locations (Program Files\NVIDIA Corporation\NVSMI, System32) when nvidia-smi is not on PATH. Prevents silent CPU-only provisioning on machines that have a GPU but a broken PATH. 2. Triton: check $LASTEXITCODE after pip install and print [WARN] on failure instead of unconditional [OK]. 3. Stale llama-server: check CMakeCache.txt for GGML_CUDA setting and rebuild if the existing binary does not match the current GPU mode (e.g. CUDA binary on a now-CPU-only rerun, or vice versa). * Fix frontend rebuild detection and npm dependency issues Addresses reviewer feedback on the frontend caching logic: 1. setup.sh: Fix broken find command that caused exit under pipefail. The piped `find | xargs find -newer` had paths after the expression which GNU find rejects. Replaced with a simpler `find -maxdepth 1 -type f -newer dist/` that checks ALL top-level files (catches index.html, bun.lock, etc. that the extension allowlist missed). 2. setup.sh: Guard oxc-validator npm install behind `command -v npm` check. When the frontend build is skipped (dist/ is cached), Node bootstrap is also skipped, so npm may not be available. 3. setup.ps1: Replace Get-ChildItem -Include with explicit path probing for src/ and public/. PowerShell's -Include without a trailing wildcard silently returns nothing, so src/public changes were never detected. Also check ALL top-level files instead of just .json/.ts/.js/.mjs extensions. * Fix studio setup: venv isolation, centralized .venv_t5, uv targeting - All platforms (including Colab) now create ~/.unsloth/studio/.venv with --without-pip fallback for broken ensurepip environments - Add --python sys.executable to uv pip install in install_python_stack.py so uv targets the correct venv instead of system Python - Centralize .venv_t5 bootstrap in transformers_version.py with proper validation (checks required packages exist, not just non-empty dir) - Replace ~150 lines of duplicated install code across 3 worker files with calls to the shared _ensure_venv_t5_exists() helper - Use uv-if-present with pip fallback; do not install uv at runtime - Add site.addsitedir() shim in colab.py so notebook cells can import studio packages from the venv without system-Python double-install - Update .venv_t5 packages: huggingface_hub 1.3.0->1.7.1, add hf_xet - Bump transformers pin 4.57.1->4.57.6 in requirements + constraints - Add Fast-Install helper to setup.ps1 with uv+pip fallback - Keep Colab-specific completion banner in setup.sh * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix nvidia-smi PATH persistence and cmake requirement for CPU-only 1. Store nvidia-smi as an absolute path ($NvidiaSmiExe) on first detection. All later calls (Get-CudaComputeCapability, Get-PytorchCudaTag, CUDA toolkit detection) use this absolute path instead of relying on PATH. This survives Refresh-Environment which rebuilds PATH from the registry and drops process-only additions. 2. Make cmake fatal for CPU-only installs. CPU-only machines depend entirely on llama-server for GGUF chat mode, so reporting "Setup Complete!" without it is misleading. GPU machines can still skip the llama-server build since they have other inference paths. * Fix broken frontend freshness detection in setup scripts - setup.sh: Replace broken `find | xargs find -newer` pipeline with single `find ... -newer` call. The old pipeline produced "paths must precede expression" errors (silently suppressed by 2>/dev/null), causing top-level config changes to never trigger a rebuild. - setup.sh: Add `command -v npm` guard to oxc-validator block so it does not fail when Node was not installed (build-skip path). - setup.ps1: Replace `Get-ChildItem -Include` (unreliable without -Recurse on PS 5.1) with explicit directory paths for src/ and public/ scanning. - Both: Add *.html to tracked file patterns so index.html (Vite entry point) changes trigger a rebuild. - Both: Use -print -quit instead of piping to head -1 for efficiency. * Fix bugs found during review of PRs #4404, #4400, #4399 - setup.sh: Add || true guard to find command that checks frontend/src and frontend/public dirs, preventing script abort under set -euo pipefail when either directory is missing - colab.py: Use sys.path.insert(0, ...) instead of site.addsitedir() so Studio venv packages take priority over system copies. Add warning when venv is missing instead of silently failing. - transformers_version.py: _venv_t5_is_valid() now checks installed package versions via .dist-info metadata, not just directory presence. Prevents false positives from stale or wrong-version packages. - transformers_version.py: _install_to_venv_t5() now passes --upgrade so pip replaces existing stale packages in the target directory. - setup.ps1: CPU-only PyTorch install uses --index-url for cpu wheel and all install commands use Fast-Install (uv with pip fallback). * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix _venv_t5_is_valid dist-info loop exiting after first directory Remove premature break that caused the loop over .dist-info directories to exit after the first match even if it had no METADATA file. Now continues iterating until a valid METADATA is found or all dirs are exhausted. * Capture error output on failure instead of discarding with Out-Null setup.ps1: 6 locations changed from `| Out-Null` to `| Out-String` with output shown on failure -- PyTorch GPU/CPU install, Triton install, venv_t5 package loop, cmake llama-server and llama-quantize builds. transformers_version.py: clean stale .venv_t5 directory before reinstall when validation detects missing or version-mismatched packages. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix ModuleNotFoundError when CLI imports studio.backend.core The backend uses bare "from utils.*" imports everywhere, relying on backend/ being on sys.path. Workers and routes add it at startup, but the CLI imports studio.backend.core as a package -- backend/ was never added. Add sys.path setup at the top of core/__init__.py so lazy imports resolve correctly regardless of entry point. Fixes: unsloth inference unsloth/Qwen3-8B "who are you" crashing with "No module named 'utils'" * Fix frontend freshness check to detect all top-level file changes The extension allowlist (*.json, *.ts, *.js, *.mjs, *.html) missed files like bun.lock, so lockfile-only dependency changes could skip the frontend rebuild. Check all top-level files instead. * Add tiktoken to .venv_t5 for Qwen-family tokenizers Qwen models use tiktoken-based tokenizers which fail when routed through the transformers 5.x overlay without tiktoken installed. Add it to the setup scripts (with deps for Windows) and runtime fallback list. Integrates PR #4418. * Fix tiktoken crash in _venv_t5_is_valid and stray brace in setup.ps1 _venv_t5_is_valid() crashed with ValueError on unpinned packages like "tiktoken" (no ==version). Handle by splitting safely and skipping version check for unpinned packages (existence check only). Also remove stray closing brace in setup.ps1 tiktoken install block. --------- Co-authored-by: Daniel Han <danielhanchen@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
430 lines
14 KiB
Python
430 lines
14 KiB
Python
#!/usr/bin/env python3
|
|
|
|
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
|
|
|
|
"""Cross-platform Python dependency installer for Unsloth Studio.
|
|
|
|
Called by both setup.sh (Linux / WSL) and setup.ps1 (Windows) after the
|
|
virtual environment is already activated. Expects `pip` and `python` on
|
|
PATH to point at the venv.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import shutil
|
|
import subprocess
|
|
import sys
|
|
import tempfile
|
|
import urllib.request
|
|
from pathlib import Path
|
|
|
|
IS_WINDOWS = sys.platform == "win32"
|
|
|
|
# ── Verbosity control ──────────────────────────────────────────────────────────
|
|
# By default the installer shows a minimal progress bar (one line, in-place).
|
|
# Set UNSLOTH_VERBOSE=1 in the environment to restore full per-step output:
|
|
# Linux/Mac: UNSLOTH_VERBOSE=1 ./studio/setup.sh
|
|
# Windows: $env:UNSLOTH_VERBOSE="1" ; .\studio\setup.ps1
|
|
VERBOSE: bool = os.environ.get("UNSLOTH_VERBOSE", "0") == "1"
|
|
|
|
# Progress bar state — updated by _progress() as each install step runs.
|
|
# _TOTAL counts: pip-upgrade + 7 shared steps + triton (non-Windows) + local-plugin + finalize
|
|
# Update _TOTAL here if you add or remove install steps in install_python_stack().
|
|
_STEP: int = 0
|
|
_TOTAL: int = 0 # set at runtime in install_python_stack() based on platform
|
|
|
|
# ── Paths ──────────────────────────────────────────────────────────────
|
|
SCRIPT_DIR = Path(__file__).resolve().parent
|
|
REQ_ROOT = SCRIPT_DIR / "backend" / "requirements"
|
|
SINGLE_ENV = REQ_ROOT / "single-env"
|
|
CONSTRAINTS = SINGLE_ENV / "constraints.txt"
|
|
LOCAL_DD_UNSTRUCTURED_PLUGIN = (
|
|
SCRIPT_DIR / "backend" / "plugins" / "data-designer-unstructured-seed"
|
|
)
|
|
|
|
# ── Color support ──────────────────────────────────────────────────────
|
|
|
|
|
|
def _enable_colors() -> bool:
|
|
"""Try to enable ANSI color support. Returns True if available."""
|
|
if not hasattr(sys.stdout, "fileno"):
|
|
return False
|
|
try:
|
|
if not os.isatty(sys.stdout.fileno()):
|
|
return False
|
|
except Exception:
|
|
return False
|
|
if IS_WINDOWS:
|
|
try:
|
|
import ctypes
|
|
|
|
kernel32 = ctypes.windll.kernel32
|
|
# Enable ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x0004) on stdout
|
|
handle = kernel32.GetStdHandle(-11) # STD_OUTPUT_HANDLE
|
|
mode = ctypes.c_ulong()
|
|
kernel32.GetConsoleMode(handle, ctypes.byref(mode))
|
|
kernel32.SetConsoleMode(handle, mode.value | 0x0004)
|
|
return True
|
|
except Exception:
|
|
return False
|
|
return True # Unix terminals support ANSI by default
|
|
|
|
|
|
# Colors disabled — Colab and most CI runners render ANSI fine, but plain output
|
|
# is cleaner in the notebook cell. Re-enable by setting _HAS_COLOR = _enable_colors()
|
|
_HAS_COLOR = False
|
|
|
|
|
|
def _green(msg: str) -> str:
|
|
return f"\033[92m{msg}\033[0m" if _HAS_COLOR else msg
|
|
|
|
|
|
def _cyan(msg: str) -> str:
|
|
return f"\033[96m{msg}\033[0m" if _HAS_COLOR else msg
|
|
|
|
|
|
def _red(msg: str) -> str:
|
|
return f"\033[91m{msg}\033[0m" if _HAS_COLOR else msg
|
|
|
|
|
|
def _progress(label: str) -> None:
|
|
"""Print an in-place progress bar for the current install step.
|
|
|
|
Uses only stdlib (sys.stdout) — no extra packages required.
|
|
In VERBOSE mode this is a no-op; per-step labels are printed by run() instead.
|
|
"""
|
|
global _STEP
|
|
_STEP += 1
|
|
if VERBOSE:
|
|
return # verbose mode: run() already printed the label
|
|
width = 20
|
|
filled = int(width * _STEP / _TOTAL)
|
|
bar = "=" * filled + "-" * (width - filled)
|
|
end = "\n" if _STEP >= _TOTAL else "" # newline only on the final step
|
|
sys.stdout.write(f"\r[{bar}] {_STEP:2}/{_TOTAL} {label:<40}{end}")
|
|
sys.stdout.flush()
|
|
|
|
|
|
def run(
|
|
label: str, cmd: list[str], *, quiet: bool = True
|
|
) -> subprocess.CompletedProcess[bytes]:
|
|
"""Run a command; on failure print output and exit."""
|
|
if VERBOSE:
|
|
print(f" {label}...")
|
|
result = subprocess.run(
|
|
cmd,
|
|
stdout = subprocess.PIPE if quiet else None,
|
|
stderr = subprocess.STDOUT if quiet else None,
|
|
)
|
|
if result.returncode != 0:
|
|
print(_red(f"❌ {label} failed (exit code {result.returncode}):"))
|
|
if result.stdout:
|
|
print(result.stdout.decode(errors = "replace"))
|
|
sys.exit(result.returncode)
|
|
return result
|
|
|
|
|
|
# Packages to skip on Windows (require special build steps)
|
|
WINDOWS_SKIP_PACKAGES = {"open_spiel", "triton_kernels"}
|
|
|
|
# ── uv bootstrap ──────────────────────────────────────────────────────
|
|
|
|
USE_UV = False # Set by _bootstrap_uv() at the start of install_python_stack()
|
|
UV_NEEDS_SYSTEM = False # Set by _bootstrap_uv() via probe
|
|
|
|
|
|
def _bootstrap_uv() -> bool:
|
|
"""Check if uv is available and probe whether --system is needed."""
|
|
global UV_NEEDS_SYSTEM
|
|
if not shutil.which("uv"):
|
|
return False
|
|
# Probe: try a dry-run install targeting the current Python explicitly.
|
|
# Without --python, uv can ignore the activated venv on some platforms.
|
|
probe = subprocess.run(
|
|
["uv", "pip", "install", "--dry-run", "--python", sys.executable, "pip"],
|
|
stdout = subprocess.PIPE,
|
|
stderr = subprocess.STDOUT,
|
|
)
|
|
if probe.returncode != 0:
|
|
# Retry with --system (some envs need it when uv can't find a venv)
|
|
probe_sys = subprocess.run(
|
|
["uv", "pip", "install", "--dry-run", "--system", "pip"],
|
|
stdout = subprocess.PIPE,
|
|
stderr = subprocess.STDOUT,
|
|
)
|
|
if probe_sys.returncode != 0:
|
|
return False # uv is broken, fall back to pip
|
|
UV_NEEDS_SYSTEM = True
|
|
return True
|
|
|
|
|
|
def _filter_requirements(req: Path, skip: set[str]) -> Path:
|
|
"""Return a temp copy of a requirements file with certain packages removed."""
|
|
lines = req.read_text(encoding = "utf-8").splitlines(keepends = True)
|
|
filtered = [
|
|
line
|
|
for line in lines
|
|
if not any(line.strip().lower().startswith(pkg) for pkg in skip)
|
|
]
|
|
tmp = tempfile.NamedTemporaryFile(
|
|
mode = "w",
|
|
suffix = ".txt",
|
|
delete = False,
|
|
encoding = "utf-8",
|
|
)
|
|
tmp.writelines(filtered)
|
|
tmp.close()
|
|
return Path(tmp.name)
|
|
|
|
|
|
def _translate_pip_args_for_uv(args: tuple[str, ...]) -> list[str]:
|
|
"""Translate pip flags to their uv equivalents."""
|
|
translated: list[str] = []
|
|
for arg in args:
|
|
if arg == "--no-cache-dir":
|
|
continue # uv cache is fast; drop this flag
|
|
elif arg == "--force-reinstall":
|
|
translated.append("--reinstall")
|
|
else:
|
|
translated.append(arg)
|
|
return translated
|
|
|
|
|
|
def _build_pip_cmd(args: tuple[str, ...]) -> list[str]:
|
|
"""Build a standard pip install command."""
|
|
cmd = [sys.executable, "-m", "pip", "install"]
|
|
cmd.extend(args)
|
|
return cmd
|
|
|
|
|
|
def _build_uv_cmd(args: tuple[str, ...]) -> list[str]:
|
|
"""Build a uv pip install command with translated flags."""
|
|
cmd = ["uv", "pip", "install"]
|
|
if UV_NEEDS_SYSTEM:
|
|
cmd.append("--system")
|
|
# Always pass --python so uv targets the correct environment.
|
|
# Without this, uv can ignore an activated venv and install into
|
|
# the system Python (observed on Colab and similar environments).
|
|
cmd.extend(["--python", sys.executable])
|
|
cmd.extend(_translate_pip_args_for_uv(args))
|
|
cmd.append("--torch-backend=auto")
|
|
return cmd
|
|
|
|
|
|
def pip_install(
|
|
label: str,
|
|
*args: str,
|
|
req: Path | None = None,
|
|
constrain: bool = True,
|
|
) -> None:
|
|
"""Build and run a pip install command (uses uv when available, falls back to pip)."""
|
|
constraint_args: list[str] = []
|
|
if constrain and CONSTRAINTS.is_file():
|
|
constraint_args = ["-c", str(CONSTRAINTS)]
|
|
|
|
actual_req = req
|
|
if req is not None and IS_WINDOWS and WINDOWS_SKIP_PACKAGES:
|
|
actual_req = _filter_requirements(req, WINDOWS_SKIP_PACKAGES)
|
|
req_args: list[str] = []
|
|
if actual_req is not None:
|
|
req_args = ["-r", str(actual_req)]
|
|
|
|
try:
|
|
if USE_UV:
|
|
uv_cmd = _build_uv_cmd(args) + constraint_args + req_args
|
|
if VERBOSE:
|
|
print(f" {label}...")
|
|
result = subprocess.run(
|
|
uv_cmd,
|
|
stdout = subprocess.PIPE,
|
|
stderr = subprocess.STDOUT,
|
|
)
|
|
if result.returncode == 0:
|
|
return
|
|
print(_red(f" uv failed, falling back to pip..."))
|
|
if result.stdout:
|
|
print(result.stdout.decode(errors = "replace"))
|
|
|
|
pip_cmd = _build_pip_cmd(args) + constraint_args + req_args
|
|
run(f"{label} (pip)" if USE_UV else label, pip_cmd)
|
|
finally:
|
|
if actual_req is not None and actual_req != req:
|
|
actual_req.unlink(missing_ok = True)
|
|
|
|
|
|
def download_file(url: str, dest: Path) -> None:
|
|
"""Download a file using urllib (no curl dependency)."""
|
|
urllib.request.urlretrieve(url, dest)
|
|
|
|
|
|
def patch_package_file(package_name: str, relative_path: str, url: str) -> None:
|
|
"""Download a file from url and overwrite a file inside an installed package."""
|
|
result = subprocess.run(
|
|
[sys.executable, "-m", "pip", "show", package_name],
|
|
capture_output = True,
|
|
text = True,
|
|
)
|
|
if result.returncode != 0:
|
|
print(_red(f" ⚠️ Could not find package {package_name}, skipping patch"))
|
|
return
|
|
|
|
location = None
|
|
for line in result.stdout.splitlines():
|
|
if line.lower().startswith("location:"):
|
|
location = line.split(":", 1)[1].strip()
|
|
break
|
|
|
|
if not location:
|
|
print(_red(f" ⚠️ Could not determine location of {package_name}"))
|
|
return
|
|
|
|
dest = Path(location) / relative_path
|
|
print(_cyan(f" Patching {dest.name} in {package_name}..."))
|
|
download_file(url, dest)
|
|
|
|
|
|
# ── Main install sequence ─────────────────────────────────────────────
|
|
|
|
|
|
def install_python_stack() -> int:
|
|
global USE_UV, _STEP, _TOTAL
|
|
_STEP = 0
|
|
_TOTAL = 10 if IS_WINDOWS else 11
|
|
|
|
# 1. Upgrade pip (needed even with uv as fallback and for bootstrapping)
|
|
_progress("pip upgrade")
|
|
run("Upgrading pip", [sys.executable, "-m", "pip", "install", "--upgrade", "pip"])
|
|
|
|
# Try to use uv for faster installs
|
|
USE_UV = _bootstrap_uv()
|
|
|
|
# 2. Core packages: unsloth-zoo + unsloth
|
|
_progress("base packages")
|
|
pip_install(
|
|
"Installing base packages",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "base.txt",
|
|
)
|
|
|
|
# 3. Extra dependencies
|
|
_progress("unsloth extras")
|
|
pip_install(
|
|
"Installing additional unsloth dependencies",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "extras.txt",
|
|
)
|
|
|
|
# 3b. Extra dependencies (no-deps) — audio model support etc.
|
|
_progress("extra codecs")
|
|
pip_install(
|
|
"Installing extras (no-deps)",
|
|
"--no-deps",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "extras-no-deps.txt",
|
|
)
|
|
|
|
# 4. Overrides (torchao, transformers) — force-reinstall
|
|
_progress("dependency overrides")
|
|
pip_install(
|
|
"Installing dependency overrides",
|
|
"--force-reinstall",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "overrides.txt",
|
|
)
|
|
|
|
# 5. Triton kernels (no-deps, from source)
|
|
if not IS_WINDOWS:
|
|
_progress("triton kernels")
|
|
pip_install(
|
|
"Installing triton kernels",
|
|
"--no-deps",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "triton-kernels.txt",
|
|
constrain = False,
|
|
)
|
|
|
|
# # 6. Patch: override llama_cpp.py with fix from unsloth-zoo feature/llama-cpp-windows-support branch
|
|
# patch_package_file(
|
|
# "unsloth-zoo",
|
|
# os.path.join("unsloth_zoo", "llama_cpp.py"),
|
|
# "https://raw.githubusercontent.com/unslothai/unsloth-zoo/refs/heads/main/unsloth_zoo/llama_cpp.py",
|
|
# )
|
|
|
|
# # 7a. Patch: override vision.py with fix from unsloth PR #4091
|
|
# patch_package_file(
|
|
# "unsloth",
|
|
# os.path.join("unsloth", "models", "vision.py"),
|
|
# "https://raw.githubusercontent.com/unslothai/unsloth/80e0108a684c882965a02a8ed851e3473c1145ab/unsloth/models/vision.py",
|
|
# )
|
|
|
|
# # 7b. Patch : override save.py with fix from feature/llama-cpp-windows-support
|
|
# patch_package_file(
|
|
# "unsloth",
|
|
# os.path.join("unsloth", "save.py"),
|
|
# "https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/unsloth/save.py",
|
|
# )
|
|
|
|
# 8. Studio dependencies
|
|
_progress("studio deps")
|
|
pip_install(
|
|
"Installing studio dependencies",
|
|
"--no-cache-dir",
|
|
req = REQ_ROOT / "studio.txt",
|
|
)
|
|
|
|
# 9. Data-designer dependencies
|
|
_progress("data designer deps")
|
|
pip_install(
|
|
"Installing data-designer base dependencies",
|
|
"--no-cache-dir",
|
|
req = SINGLE_ENV / "data-designer-deps.txt",
|
|
)
|
|
|
|
# 10. Data-designer packages (no-deps to avoid conflicts)
|
|
_progress("data designer")
|
|
pip_install(
|
|
"Installing data-designer",
|
|
"--no-cache-dir",
|
|
"--no-deps",
|
|
req = SINGLE_ENV / "data-designer.txt",
|
|
)
|
|
|
|
# 11. Local Data Designer seed plugin
|
|
if not LOCAL_DD_UNSTRUCTURED_PLUGIN.is_dir():
|
|
print(
|
|
_red(
|
|
f"❌ Missing local plugin directory: {LOCAL_DD_UNSTRUCTURED_PLUGIN}",
|
|
),
|
|
)
|
|
return 1
|
|
_progress("local plugin")
|
|
pip_install(
|
|
"Installing local data-designer unstructured plugin",
|
|
"--no-cache-dir",
|
|
"--no-deps",
|
|
str(LOCAL_DD_UNSTRUCTURED_PLUGIN),
|
|
constrain = False,
|
|
)
|
|
|
|
# 12. Patch metadata for single-env compatibility
|
|
_progress("finalizing")
|
|
run(
|
|
"Patching single-env metadata",
|
|
[sys.executable, str(SINGLE_ENV / "patch_metadata.py")],
|
|
)
|
|
|
|
# 13. Final check (silent; third-party conflicts are expected)
|
|
subprocess.run(
|
|
[sys.executable, "-m", "pip", "check"],
|
|
stdout = subprocess.DEVNULL,
|
|
stderr = subprocess.DEVNULL,
|
|
)
|
|
|
|
print(_green("✅ Python dependencies installed"))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(install_python_stack())
|