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
Update wheel builds to strip debug (#6161)
Simon Mo committed
Jul 5, 2024 at 14:51 UTC
2de490d60f281c8d4b182bf5551d27c141bd742d
1 file changed
+1
-1
.buildkite/release-pipeline.yaml
+1
-1
@@ -5,7 +5,7 @@ steps:
5
agents:
6
queue: cpu_queue
7
commands:
8
- - "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 ."
8
+ - "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 ."
9
- "mkdir artifacts"
10
- "docker run --rm -v $(pwd)/artifacts:/artifacts_host vllm-ci:build-image cp -r dist /artifacts_host"
11
- "aws s3 cp --recursive artifacts/dist s3://vllm-wheels/$BUILDKITE_COMMIT/"