@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 114b0e2500
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 12, 21:00 UTC

[chore] Update annotate release scripts (#29077)

Signed-off-by: Kevin H. Luu <khluu000@gmail.com>

Kevin H. Luu committed Nov 20, 2025 at 10:22 UTC 114b0e25004b7e7cf0a23dc65f407471bd5de7e8
1 file changed +5 -4
.buildkite/scripts/annotate-release.sh
+5 -4
@@ -23,8 +23,8 @@ To download the wheel (by version):
23 aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}/vllm-${RELEASE_VERSION}-cp38-abi3-manylinux1_x86_64.whl .
24 aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}/vllm-${RELEASE_VERSION}-cp38-abi3-manylinux2014_aarch64.whl .
25
26 -aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu126/vllm-${RELEASE_VERSION}+cu126-cp38-abi3-manylinux1_x86_64.whl .
26 aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu129/vllm-${RELEASE_VERSION}+cu129-cp38-abi3-manylinux1_x86_64.whl .
27 +aws s3 cp s3://vllm-wheels/${RELEASE_VERSION}+cu130/vllm-${RELEASE_VERSION}+cu130-cp38-abi3-manylinux1_x86_64.whl .
28 \`\`\`
29
30 To download and upload the image:
@@ -45,9 +45,10 @@ docker tag vllm/vllm-openai:aarch64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
45 docker push vllm/vllm-openai:latest-aarch64
46 docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
47
48 -docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64 --amend
49 -docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64 --amend
48 +docker manifest rm vllm/vllm-openai:latest
49 +docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64
50 +docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
51 docker manifest push vllm/vllm-openai:latest
52 docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}
53 \`\`\`
53 -EOF
\ No newline at end of file
54 +EOF