@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 5c9121203c
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 15, 13:30 UTC

[release] Publish neuron docker image (#16733)

Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com>

omrishiv committed Apr 19, 2025 at 01:11 UTC 5c9121203cc34e781f1f249b69cb789244e861f0
1 file changed +15
.buildkite/release-pipeline.yaml
+15
@@ -86,3 +86,18 @@ steps:
86 - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
87 env:
88 DOCKER_BUILDKIT: "1"
89 +
90 + - block: "Build Neuron release image"
91 + key: block-neuron-release-image-build
92 + depends_on: ~
93 +
94 + - label: "Build and publish Neuron release image"
95 + depends_on: block-neuron-release-image-build
96 + agents:
97 + queue: neuron-postmerge
98 + commands:
99 + - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
100 + - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:$(buildkite-agent meta-data get release-version) --tag public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:latest --progress plain -f docker/Dockerfile.neuron ."
101 + - "docker push public.ecr.aws/q9t5s3a7/vllm-neuron-release-repo:$(buildkite-agent meta-data get release-version)"
102 + env:
103 + DOCKER_BUILDKIT: "1"