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 wheel build env var (#6162)
Simon Mo committed
Jul 5, 2024 at 16:24 UTC
f0250620dd2e33087293cf89b96db854767b939b
1 file changed
+2
-2
.buildkite/release-pipeline.yaml
+2
-2
@@ -5,9 +5,9 @@ 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 -e CMAKE_BUILD_TYPE=Release --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 --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"
10
+ - "docker run --rm -v $(pwd)/artifacts:/artifacts_host -e CMAKE_BUILD_TYPE=Release vllm-ci:build-image cp -r dist /artifacts_host"
11
- "aws s3 cp --recursive artifacts/dist s3://vllm-wheels/$BUILDKITE_COMMIT/"
12
matrix:
13
setup: