biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Build] Supports CUDA 12.6 and 11.8 after Blackwell Update (#18316)

Browse Source 
Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Simon Mo
2025-05-18 23:19:33 -07:00
committed by GitHub
parent 27d0952600
commit 47fda6d089
2 changed files with 9 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docker/Dockerfile
View File

@@ -257,8 +257,13 @@ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
# uv pip install --system https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.4/flashinfer_python-0.2.4+cu124torch2.6-cp38-abi3-linux_x86_64.whl ; \
# TESTING: install FlashInfer from source to test 2.7.0 final RC
FLASHINFER_ENABLE_AOT=1 TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0 10.0+PTX' \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@e00e8cedbfcb220f328fd36aa8f529f869b01e6b" ; \
if [[ "$CUDA_VERSION" == 12.8* ]]; then \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0 10.0+PTX'; \
else \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0+PTX'; \
fi && \
export FLASHINFER_ENABLE_AOT=1; \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@21ea1d2545f74782b91eb8c08fd503ac4c0743fc" ; \
fi
COPY examples examples
COPY benchmarks benchmarks