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

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
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 9 additions and 4 deletions

View File

@ -14,7 +14,7 @@ steps:
agents:
queue: cpu_queue_postmerge
commands:
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.6.3 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.6.3 --build-arg torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0+PTX' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "mkdir artifacts"
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
- "bash .buildkite/scripts/upload-wheels.sh"
@ -31,7 +31,7 @@ steps:
agents:
queue: cpu_queue_postmerge
commands:
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=11.8.0 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=11.8.0 --build-arg torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0+PTX' --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
- "mkdir artifacts"
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image bash -c 'cp -r dist /artifacts_host && chmod -R a+rw /artifacts_host'"
- "bash .buildkite/scripts/upload-wheels.sh"

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