xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 08:56:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

Install pre-built xformers-0.0.32.post2 built with pt-2.9.0 (#27598)

Browse Source 
Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
This commit is contained in:
Huy Do 2025-10-28 19:39:15 -07:00 committed by GitHub
parent 0b51c9bd8b
commit f257544709
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docker/Dockerfile
View File

@ -361,13 +361,6 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
&& uv pip install --system dist/*.whl --verbose \ && uv pip install --system dist/*.whl --verbose \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# TODO (huydhn): Remove this once xformers is released for 2.9.0
RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
. /etc/environment
export TORCH_CUDA_ARCH_LIST='7.5 8.0+PTX 9.0a'
uv pip install --system --no-build-isolation "git+https://github.com/facebookresearch/xformers@v0.0.32.post2"
BASH
# Install FlashInfer pre-compiled kernel cache and binaries # Install FlashInfer pre-compiled kernel cache and binaries
# https://docs.flashinfer.ai/installation.html # https://docs.flashinfer.ai/installation.html
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \

2
requirements/cuda.txt
View File

@ -10,7 +10,7 @@ torchaudio==2.9.0
# These must be updated alongside torch # These must be updated alongside torch
torchvision==0.24.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version torchvision==0.24.0 # Required for phi3v processor. See https://github.com/pytorch/vision?tab=readme-ov-file#installation for corresponding version
# https://github.com/facebookresearch/xformers/releases/tag/v0.0.32.post1 # https://github.com/facebookresearch/xformers/releases/tag/v0.0.32.post1
# xformers==0.0.32.post1; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch >= 2.8 xformers==0.0.33+5d4b92a5.d20251026; platform_system == 'Linux' and platform_machine == 'x86_64' # Requires PyTorch >= 2.9
# FlashInfer should be updated together with the Dockerfile # FlashInfer should be updated together with the Dockerfile
flashinfer-python==0.4.1 flashinfer-python==0.4.1
# Triton Kernels are needed for mxfp4 fused moe. (Should be updated alongside torch) # Triton Kernels are needed for mxfp4 fused moe. (Should be updated alongside torch)