A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
Update CUDA architecture list in build pipeline for 12.9.1 wheels (#26592)
Signed-off-by: Will Eaton <wseaton@users.noreply.github.com>
Will Eaton committed
Oct 10, 2025 at 14:15 UTC
3b780a4bbb6ee9e0ff69dc6557611d6ba4e24d3f
1 file changed
+1
-1
.buildkite/release-pipeline.yaml
+1
-1
@@ -48,7 +48,7 @@ steps:
48
agents:
49
queue: cpu_queue_postmerge
50
commands:
51
- - "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=12.9.1 --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 ."
51
+ - "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=12.9.1 --tag vllm-ci:build-image --target build --progress plain -f docker/Dockerfile ."
52
- "mkdir artifacts"
53
- "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'"
54
- "bash .buildkite/scripts/upload-wheels.sh"