Move to new cluster

.github/workflows/build.yaml

@@ -28,7 +28,7 @@ jobs:
       group: ${{ github.workflow }}-build-and-push-image-${{ inputs.hardware }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
     # TODO see with @Glegendre to get CPU runner here instead
-    runs-on: [self-hosted, intel-cpu, 32-cpu, 256-ram, ci]
+    runs-on: aws-east1-intel-32-cpu-256-ram
     permissions:
       contents: write
       packages: write
@@ -81,7 +81,7 @@ jobs:
           install: true
           config-inline: |
             [registry."docker.io"]
-              mirrors = ["registry.github-runners.huggingface.tech"]
+              mirrors = ["registry-us-east-1.prod.aws.ci.huggingface.tech"]
       - name: Login to GitHub Container Registry
         if: github.event_name != 'pull_request'
         uses: docker/login-action@v3
@@ -103,7 +103,7 @@ jobs:
         uses: docker/metadata-action@v5
         with:
           images: |
-            registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference
+            registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference
           tags: |
             type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
       # If main, release or tag
@@ -115,7 +115,7 @@ jobs:
           flavor: |
             latest=auto
           images: |
-            registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference
+            registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference
             ghcr.io/huggingface/text-generation-inference
             db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
           tags: |
@@ -138,10 +138,46 @@ jobs:
           labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}          
           cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
           cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
+      # If main, trigger sync registry
+      - name: Extract metadata (tags, labels) for Internal Registry
+        if: ${{ github.event_name != 'pull_request' }}
+        id: meta-internal-registry
+        uses: docker/[email protected]
+        with:
+          flavor: |
+            latest=auto
+          images: |
+            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
+          tags: |
+            type=semver,pattern={{version}}${{ env.LABEL }}
+            type=semver,pattern={{major}}.{{minor}}${{ env.LABEL }}
+            type=raw,value=latest${{ env.LABEL }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
+      - name: Tailscale
+        if: ${{ github.event_name != 'pull_request' }}
+        uses: huggingface/tailscale-action@main
+        with:
+          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
+          slackChannel: ${{ secrets.SLACK_CIFEEDBACK_CHANNEL }}
+          slackToken: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+      - name: Sync to internal registry
+        if: ${{ github.event_name != 'pull_request' }}
+        id: sync-internal-registry
+        uses: the-actions-org/workflow-dispatch@v4
+        with:
+          workflow: build.yaml
+          repo: ${{ secrets.SYNC_REGISTRY_REPO }}
+          wait-for-completion: true
+          wait-for-completion-interval: 10s
+          display-workflow-run-url-interval: 10s
+          ref: refs/heads/main
+          token: ${{ secrets.SYNC_REGISTRY_TOKEN }}
+          inputs: '{"source_image": "registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}", "destination_image": "${{ join(steps.meta-internal-registry.outputs.tags,'','') }}" }'
+
       - name: Final
         id: final
         run: |
-          echo "docker_image=registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT}}${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
+          echo "docker_image=registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT}}${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
           echo "docker_devices=${{ env.DOCKER_DEVICES }}" >> "$GITHUB_OUTPUT"
           echo "runs_on=${{ env.RUNS_ON }}" >> "$GITHUB_OUTPUT"
           echo "label=${{ env.LABEL }}" >> "$GITHUB_OUTPUT"