@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 21b2dcedab
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 release pipeline's -e flag (#6390)

Simon Mo committed Jul 12, 2024 at 14:08 UTC 21b2dcedabb84332a73e8cda3886a6988c52a7df
1 file changed +1 -1
.buildkite/release-pipeline.yaml
+1 -1
@@ -3,7 +3,7 @@ steps:
3 agents:
4 queue: cpu_queue
5 commands:
6 - - "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 -e CMAKE_BUILD_TYPE=Release --target build --progress plain ."
6 + - "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 ."
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