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 16, 22:00 UTC
Fix release-pipeline.yaml (#6388)
Simon Mo committed
Jul 12, 2024 at 14:00 UTC
bb1a784b05cde68a2a657431c4ab21839ca4c756
1 file changed
+1
-1
.buildkite/release-pipeline.yaml
+1
-1
@@ -27,7 +27,7 @@ steps:
27
- "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg CUDA_VERSION={{matrix.cuda_version}} --build-arg PYTHON_VERSION={{matrix.python_version}} --tag vllm-ci:build-image --target build --progress plain ."
28
- "mkdir artifacts"
29
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image cp -r dist /artifacts_host"
30
- - "for f in artifacts/dist/*.whl; do mv -- \"$f\" \"${f/linux/manylinux1}\"; done
30
+ - "for f in artifacts/dist/*.whl; do mv -- \"$f\" \"${f/linux/manylinux1}\"; done"
31
- "aws s3 cp --recursive --acl public-read artifacts/dist s3://vllm-wheels/$BUILDKITE_COMMIT/"
32
- "aws s3 cp --recursive --acl public-read artifacts/dist s3://vllm-wheels/nightly/"
33
matrix: