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 9, 01:15 UTC
[CI/Build] add directions for CPU image upload to Docker Hub (#32032)
Signed-off-by: Nathan Weinberg <nweinber@redhat.com> Signed-off-by: Nathan Weinberg <31703736+nathan-weinberg@users.noreply.github.com> Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
Nathan Weinberg committed
Feb 2, 2026 at 21:48 UTC
1b60b45d0d745e0c0be65994507a702a19fd4761
1 file changed
+23
-1
.buildkite/scripts/annotate-release.sh
+23
-1
@@ -86,5 +86,27 @@ docker manifest create vllm/vllm-openai:latest-cu130 vllm/vllm-openai:latest-x86
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}
93
+
94
+docker tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v${RELEASE_VERSION} vllm/vllm-openai-cpu:x86_64
95
+docker tag vllm/vllm-openai-cpu:x86_64 vllm/vllm-openai-cpu:latest-x86_64
96
+docker tag vllm/vllm-openai-cpu:x86_64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64
97
+docker push vllm/vllm-openai-cpu:latest-x86_64
98
+docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64
99
+
100
+docker tag public.ecr.aws/q9t5s3a7/vllm-arm64-cpu-release-repo:v${RELEASE_VERSION} vllm/vllm-openai-cpu:arm64
101
+docker tag vllm/vllm-openai-cpu:arm64 vllm/vllm-openai-cpu:latest-arm64
102
+docker tag vllm/vllm-openai-cpu:arm64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64
103
+docker push vllm/vllm-openai-cpu:latest-arm64
104
+docker push vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64
105
+
106
+docker manifest rm vllm/vllm-openai-cpu:latest || true
107
+docker manifest create vllm/vllm-openai-cpu:latest vllm/vllm-openai-cpu:latest-x86_64 vllm/vllm-openai-cpu:latest-arm64
108
+docker manifest create vllm/vllm-openai-cpu:v${RELEASE_VERSION} vllm/vllm-openai-cpu:v${RELEASE_VERSION}-x86_64 vllm/vllm-openai-cpu:v${RELEASE_VERSION}-arm64
109
+docker manifest push vllm/vllm-openai-cpu:latest
110
+docker manifest push vllm/vllm-openai-cpu:v${RELEASE_VERSION}
111
\`\`\`
90
-EOF
112
+EOF