[CI] Push multiarch manifests as nightly builds (vllm-project#25764)

Signed-off-by: Sahithi Chigurupati <[email protected]>

Author: csahithi

.buildkite/release-pipeline.yaml

@@ -150,11 +150,16 @@ steps:
       queue: cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
-      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT vllm/vllm-openai:nightly"
-      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT vllm/vllm-openai:nightly-$BUILDKITE_COMMIT"
-      - "docker push vllm/vllm-openai:nightly"
-      - "docker push vllm/vllm-openai:nightly-$BUILDKITE_COMMIT"
+      - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64"
+      - "docker pull public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64"
+      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-x86_64 vllm/vllm-openai:nightly-x86_64"
+      - "docker tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT-aarch64 vllm/vllm-openai:nightly-aarch64"
+      - "docker push vllm/vllm-openai:nightly-x86_64"
+      - "docker push vllm/vllm-openai:nightly-aarch64"
+      - "docker manifest create vllm/vllm-openai:nightly vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
+      - "docker manifest create vllm/vllm-openai:nightly-$BUILDKITE_COMMIT vllm/vllm-openai:nightly-x86_64 vllm/vllm-openai:nightly-aarch64 --amend"
+      - "docker manifest push vllm/vllm-openai:nightly"
+      - "docker manifest push vllm/vllm-openai:nightly-$BUILDKITE_COMMIT"
       # Clean up old nightly builds (keep only last 14)
       - "bash .buildkite/scripts/cleanup-nightly-builds.sh"
     plugins:
@@ -163,3 +168,4 @@ steps:
           password-env: DOCKERHUB_TOKEN
     env:
       DOCKER_BUILDKIT: "1"
+      DOCKERHUB_USERNAME: "vllmbot"

.buildkite/scripts/cleanup-nightly-builds.sh

@@ -8,20 +8,41 @@ set -ex
 # DockerHub API endpoint for vllm/vllm-openai repository
 REPO_API_URL="https://hub.docker.com/v2/repositories/vllm/vllm-openai/tags"
 
-# Get DockerHub token from environment
+# Get DockerHub credentials from environment
 if [ -z "$DOCKERHUB_TOKEN" ]; then
     echo "Error: DOCKERHUB_TOKEN environment variable is not set"
     exit 1
 fi
 
+if [ -z "$DOCKERHUB_USERNAME" ]; then
+    echo "Error: DOCKERHUB_USERNAME environment variable is not set"
+    exit 1
+fi
+
+# Get DockerHub bearer token
+echo "Getting DockerHub bearer token..."
+set +x
+BEARER_TOKEN=$(curl -s -X POST \
+    -H "Content-Type: application/json" \
+    -d "{\"username\": \"$DOCKERHUB_USERNAME\", \"password\": \"$DOCKERHUB_TOKEN\"}" \
+    "https://hub.docker.com/v2/users/login" | jq -r '.token')
+set -x
+
+if [ -z "$BEARER_TOKEN" ] || [ "$BEARER_TOKEN" = "null" ]; then
+    echo "Error: Failed to get DockerHub bearer token"
+    exit 1
+fi
+
 # Function to get all tags from DockerHub
 get_all_tags() {
     local page=1
     local all_tags=""
 
     while true; do
-        local response=$(curl -s -H "Authorization: Bearer $DOCKERHUB_TOKEN" \
+        set +x
+        local response=$(curl -s -H "Authorization: Bearer $BEARER_TOKEN" \
             "$REPO_API_URL?page=$page&page_size=100")
+        set -x
 
         # Get both last_updated timestamp and tag name, separated by |
         local tags=$(echo "$response" | jq -r '.results[] | select(.name | startswith("nightly-")) | "\(.last_updated)|\(.name)"')
@@ -43,7 +64,9 @@ delete_tag() {
     echo "Deleting tag: $tag_name"
 
     local delete_url="https://hub.docker.com/v2/repositories/vllm/vllm-openai/tags/$tag_name"
-    local response=$(curl -s -X DELETE -H "Authorization: Bearer $DOCKERHUB_TOKEN" "$delete_url")
+    set +x
+    local response=$(curl -s -X DELETE -H "Authorization: Bearer $BEARER_TOKEN" "$delete_url")
+    set -x
 
     if echo "$response" | jq -e '.detail' > /dev/null 2>&1; then
         echo "Warning: Failed to delete tag $tag_name: $(echo "$response" | jq -r '.detail')"