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, 05:45 UTC
[ci/build] Job to build and push release image (#10877)
Kevin H. Luu committed
Dec 3, 2024 at 23:02 UTC
c9ca4fce3f48e27801e1bad03d4bc0b963567d24
1 file changed
+13
.buildkite/release-pipeline.yaml
+13
@@ -26,3 +26,16 @@ steps:
26
- "bash .buildkite/upload-wheels.sh"
27
env:
28
DOCKER_BUILDKIT: "1"
29
+
30
+ - block: "Build release image"
31
+ depends_on: ~
32
+ key: block-release-image-build
33
+
34
+ - label: "Build release image"
35
+ depends_on: block-release-image-build
36
+ agents:
37
+ queue: cpu_queue_postmerge
38
+ commands:
39
+ - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
40
+ - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.1.0 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain ."
41
+ - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"