@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 07b35af86d
Fork 0

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 interpolation in release pipeline (#6389)

Simon Mo committed Jul 12, 2024 at 14:03 UTC 07b35af86d984e529e4099b0d348b71ad820c23d
1 file changed +2 -2
.buildkite/release-pipeline.yaml
+2 -2
@@ -7,7 +7,7 @@ steps:
7 - "mkdir artifacts"
8 - "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image cp -r dist /artifacts_host"
9 # rename the files to change linux -> manylinux1
10 - - "for f in artifacts/dist/*.whl; do mv -- \"$f\" \"${f/linux/manylinux1}\"; done"
10 + - "for f in artifacts/dist/*.whl; do mv -- \"$$f\" \"$${f/linux/manylinux1}\"; done"
11 - "aws s3 cp --recursive --acl public-read artifacts/dist s3://vllm-wheels/$BUILDKITE_COMMIT/"
12 - "aws s3 cp --recursive --acl public-read artifacts/dist s3://vllm-wheels/nightly/"
13 matrix:
@@ -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: