LocalAI/backend/python/diffusers/requirements-hipblas.txt

--extra-index-url https://download.pytorch.org/whl/rocm7.0
torch==2.10.0+rocm7.0
torchvision==0.25.0+rocm7.0
git+https://github.com/huggingface/diffusers
opencv-python
transformers
accelerate
compel
peft
sentencepiece
optimum-quanto
ftfy
feat(rocm): bump to 7.x (#9323) feat(rocm): bump to 7.2.1 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2026-04-12 06:51:30 +00:00			`--extra-index-url https://download.pytorch.org/whl/rocm7.0`
			`torch==2.10.0+rocm7.0`
			`torchvision==0.25.0+rocm7.0`
chore(deps): bump torch and diffusers (#5970) * chore(ci): add backend build tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(deps): bump torch and diffusers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): run diffusers/hipblas on self-hosted Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): do not publish darwin if building from PRs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2025-08-05 12:47:01 +00:00			`git+https://github.com/huggingface/diffusers`
fix(python): move accelerate and GPU-specific libs to build-type (#3194) Some of the dependencies in `requirements.txt`, even if generic, pulls down the line CUDA libraries. This changes moves mostly all GPU-specific libs to the build-type, and tries a safer approach. In `requirements.txt` now are listed only "first-level" dependencies, for instance, grpc, but libs-dependencies are moved down to the respective build-type `requirements.txt` to avoid any mixin. This should fix #2737 and #1592. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2024-08-07 15:02:32 +00:00			`opencv-python`
chore(deps): remove pin on transformers (#5501) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2025-05-27 07:24:27 +00:00			`transformers`
fix(python): move accelerate and GPU-specific libs to build-type (#3194) Some of the dependencies in `requirements.txt`, even if generic, pulls down the line CUDA libraries. This changes moves mostly all GPU-specific libs to the build-type, and tries a safer approach. In `requirements.txt` now are listed only "first-level" dependencies, for instance, grpc, but libs-dependencies are moved down to the respective build-type `requirements.txt` to avoid any mixin. This should fix #2737 and #1592. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2024-08-07 15:02:32 +00:00			`accelerate`
			`compel`
			`peft`
fix(diffusers): use nightly rocm for hipblas builds (#3202) Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> 2024-08-08 15:28:07 +00:00			`sentencepiece`
feat(diffusers): add support for wan2.2 (#6153) * feat(diffusers): add support for wan2.2 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): use ttl.sh for PRs Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add ftfy deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Revert "chore(ci): use ttl.sh for PRs" This reverts commit c9fc3ecf288dd9d454a38d78840d214b72a140ca. * Simplify Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: do not pin torch/torchvision on cuda12 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> 2025-08-28 08:26:42 +00:00			`optimum-quanto`
			`ftfy`