re-push to internal registry

.github/workflows/build.yaml

@@ -27,8 +27,8 @@ jobs:
     concurrency:
       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:
+      group: aws-r7i-8xlarge-priv
     permissions:
       contents: write
       packages: write
@@ -49,7 +49,7 @@ jobs:
                 export dockerfile="Dockerfile"
                 export label_extension=""
                 export docker_devices=""
-                export runs_on="nvidia-gpu"
+                export runs_on="aws-g5-12xlarge"
                 ;;
             rocm)
                 export dockerfile="Dockerfile_amd"
@@ -79,9 +79,15 @@ jobs:
         uses: docker/setup-buildx-action@v3
         with:
           install: true
-          config-inline: |
+          buildkitd-config-inline: |
             [registry."docker.io"]
-              mirrors = ["registry.github-runners.huggingface.tech"]
+              mirrors = ["registry-us-east-1-mirror.prod.aws.ci.huggingface.tech"]
+      - name: Login to internal Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.REGISTRY_USERNAME }}
+          password: ${{ secrets.REGISTRY_PASSWORD }}
+          registry: registry.internal.huggingface.tech
       - name: Login to GitHub Container Registry
         if: github.event_name != 'pull_request'
         uses: docker/login-action@v3
@@ -103,7 +109,8 @@ jobs:
         uses: docker/metadata-action@v5
         with:
           images: |
-            registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference
+            registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference
+            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
           tags: |
             type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
       # If main, release or tag
@@ -115,7 +122,8 @@ jobs:
           flavor: |
             latest=auto
           images: |
-            registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference
+            registry-us-east-1.prod.aws.ci.huggingface.tech/api-inference/community/text-generation-inference
+            registry.internal.huggingface.tech/api-inference/community/text-generation-inferenceca
             ghcr.io/huggingface/text-generation-inference
             db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
           tags: |
@@ -141,7 +149,7 @@ jobs:
       - name: Final
         id: final
         run: |
-          echo "docker_image=registry-push.github-runners.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ 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"
@@ -150,7 +158,8 @@ jobs:
       group: ${{ github.workflow }}-${{ github.job }}-${{ needs.build-and-push.outputs.label }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
     needs: build-and-push
-    runs-on: ["self-hosted", "${{ needs.build-and-push.outputs.runs_on }}", "multi-gpu"]
+    runs-on:
+      group: ${{ needs.build-and-push.outputs.runs_on }}
     if: needs.build-and-push.outputs.runs_on != 'ubuntu-latest'
     env:
       PYTEST_FLAGS: ${{ (startsWith(github.ref, 'refs/tags/') || github.ref == 'refs/heads/main' || inputs.release-tests == true) && '--release' || '' }}
@@ -174,3 +183,4 @@ jobs:
           export HF_TOKEN=${{ secrets.HF_TOKEN }}
           echo $DOCKER_IMAGE
           pytest -s -vv integration-tests ${PYTEST_FLAGS}
+

.github/workflows/load_test.yaml

@@ -15,7 +15,8 @@ jobs:
     concurrency:
       group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
-    runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
+    runs-on:
+      group: aws-g5-12xlarge
     env:
       DOCKER_VOLUME: /cache
     steps: