frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update Dockerfile to build for Blackwell (#18095)

Browse Source
This commit is contained in:
Michael Goin
2025-05-17 03:23:25 -04:00
committed by GitHub
parent 48ac2bed5b
commit dcfe95234c
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docker/Dockerfile
View File

@ -77,7 +77,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.6 8.9 9.0+PTX'
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
# Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
@ -257,8 +257,8 @@ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
# uv pip install --system https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.4/flashinfer_python-0.2.4+cu124torch2.6-cp38-abi3-linux_x86_64.whl ; \
# TESTING: install FlashInfer from source to test 2.7.0 final RC
FLASHINFER_ENABLE_AOT=1 TORCH_CUDA_ARCH_LIST='7.5 8.0 8.6 8.9 9.0+PTX' \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@v0.2.4" ; \
FLASHINFER_ENABLE_AOT=1 TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0 10.0+PTX' \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@e00e8cedbfcb220f328fd36aa8f529f869b01e6b" ; \
fi
COPY examples examples
COPY benchmarks benchmarks