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 8, 21:30 UTC
[release] Minor fixes to release annotation (#33849)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
Feb 4, 2026 at 18:07 UTC
72bb24e2db2acd98a49adcb9e3f1dc6f1bbef4c0
1 file changed
+27
-22
.buildkite/scripts/annotate-release.sh
+27
-22
@@ -27,7 +27,7 @@ aws s3 cp s3://vllm-wheels/${BUILDKITE_COMMIT}/vllm-${RELEASE_VERSION}+cpu-cp38-
27
To download and upload the image:
28
29
\`\`\`
30
-Download images:
30
+# Download images:
31
32
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-x86_64
33
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-aarch64
@@ -35,8 +35,12 @@ docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-x86_64
35
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-aarch64-cu130
36
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm-base
37
docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm
38
+docker pull public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION}
39
+docker pull public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${RELEASE_VERSION}
40
39
-Tag and push images:
41
+# Tag and push images:
42
+
43
+## CUDA
44
45
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-x86_64 vllm/vllm-openai:x86_64
46
docker tag vllm/vllm-openai:x86_64 vllm/vllm-openai:latest-x86_64
@@ -62,34 +66,21 @@ docker tag vllm/vllm-openai:aarch64-cu130 vllm/vllm-openai:v${RELEASE_VERSION}-a
66
docker push vllm/vllm-openai:latest-aarch64-cu130
67
docker push vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu130
68
65
-docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-rocm
66
-docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-rocm vllm/vllm-openai-rocm:latest
67
-docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-rocm vllm/vllm-openai-rocm:v${RELEASE_VERSION}-rocm
69
+## ROCm
70
+
71
+docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}
72
+docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT} vllm/vllm-openai-rocm:latest
73
+docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT} vllm/vllm-openai-rocm:v${RELEASE_VERSION}
74
docker push vllm/vllm-openai-rocm:latest
69
-docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}-rocm
75
+docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}
76
71
-Create multi-arch manifest:
77
docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:${BUILDKITE_COMMIT}-rocm-base vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base
78
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base vllm/vllm-openai-rocm:latest-base
79
docker tag vllm/vllm-openai-rocm:${BUILDKITE_COMMIT}-base vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base
80
docker push vllm/vllm-openai-rocm:latest-base
81
docker push vllm/vllm-openai-rocm:v${RELEASE_VERSION}-base
82
78
-docker manifest rm vllm/vllm-openai:latest
79
-docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64
80
-docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
81
-docker manifest push vllm/vllm-openai:latest
82
-docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}
83
-
84
-docker manifest rm vllm/vllm-openai:latest-cu130
85
-docker manifest create vllm/vllm-openai:latest-cu130 vllm/vllm-openai:latest-x86_64-cu130 vllm/vllm-openai:latest-aarch64-cu130
86
-docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu130 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu130 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu130
87
-docker manifest push vllm/vllm-openai:latest-cu130
88
-docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu130
89
-
90
-# CPU images (vllm/vllm-openai-cpu)
91
-docker pull public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION}
92
-docker pull public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${RELEASE_VERSION}
83
+## CPU
84
85
docker tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION} vllm/vllm-openai-cpu:x86_64
86
docker tag vllm/vllm-openai-cpu:x86_64 vllm/vllm-openai-cpu:latest-x86_64
@@ -103,6 +94,20 @@ docker tag vllm/vllm-openai-cpu:arm64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-a
94
docker push vllm/vllm-openai-cpu:latest-arm64
95
docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64
96
97
+# Create multi-arch manifest:
98
+
99
+docker manifest rm vllm/vllm-openai:latest
100
+docker manifest create vllm/vllm-openai:latest vllm/vllm-openai:latest-x86_64 vllm/vllm-openai:latest-aarch64
101
+docker manifest create vllm/vllm-openai:v${RELEASE_VERSION} vllm/vllm-openai:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64
102
+docker manifest push vllm/vllm-openai:latest
103
+docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}
104
+
105
+docker manifest rm vllm/vllm-openai:latest-cu130
106
+docker manifest create vllm/vllm-openai:latest-cu130 vllm/vllm-openai:latest-x86_64-cu130 vllm/vllm-openai:latest-aarch64-cu130
107
+docker manifest create vllm/vllm-openai:v${RELEASE_VERSION}-cu130 vllm/vllm-openai:v${RELEASE_VERSION}-x86_64-cu130 vllm/vllm-openai:v${RELEASE_VERSION}-aarch64-cu130
108
+docker manifest push vllm/vllm-openai:latest-cu130
109
+docker manifest push vllm/vllm-openai:v${RELEASE_VERSION}-cu130
110
+
111
docker manifest rm vllm/vllm-openai-cpu:latest || true
112
docker manifest create vllm/vllm-openai-cpu:latest vllm/vllm-openai-cpu:latest-x86_64 vllm/vllm-openai-cpu:latest-arm64
113
docker manifest create vllm/vllm-openai-cpu:v${RELEASE_VERSION} vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64