feat(ci): custom gpu runners (#328)

.github/workflows/build.yaml

@@ -25,8 +25,44 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  start-runner:
+    name: Start self-hosted EC2 runner
+    runs-on: ubuntu-latest
+    env:
+      AWS_REGION: us-east-1
+      EC2_AMI_ID: ami-03cfed9ea28f4b002
+      EC2_INSTANCE_TYPE: g5.12xlarge
+      EC2_SUBNET_ID: subnet-931b34f5,subnet-ecb993cd,subnet-943dc2d8,subnet-45371f1a,subnet-ee93e0df,subnet-fddc3dfc
+      EC2_SECURITY_GROUP: sg-04d472c808f365022
+    outputs:
+      label: ${{ steps.start-ec2-runner.outputs.label }}
+      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
+    steps:
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v1
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ env.AWS_REGION }}
+      - name: Start EC2 runner
+        id: start-ec2-runner
+        uses: philschmid/philschmid-ec2-github-runner@main
+        with:
+          mode: start
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          ec2-image-id: ${{ env.EC2_AMI_ID }}
+          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
+          subnet-id: ${{ env.EC2_SUBNET_ID }}
+          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
+          aws-resource-tags: > # optional, requires additional permissions
+            [
+              {"Key": "Name", "Value": "ec2-tgi-github-runner"},
+              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
+            ]
+
   build-and-push-image:
-    runs-on: large-runner
+    needs: start-runner # required to start the main job when the runner is ready
+    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
     permissions:
       contents: write
       packages: write
@@ -49,7 +85,7 @@ jobs:
         with:
           cosign-release: 'v1.13.1'
       - name: Tailscale
-        uses: tailscale/github-action@v1
+        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
         with:
           authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
       - name: Login to GitHub Container Registry
@@ -136,52 +172,26 @@ jobs:
         with:
           sarif_file: 'trivy-results.sarif'
 
-  build-and-push-sagemaker-image:
+  stop-runner:
+    name: Stop self-hosted EC2 runner
     needs:
+      - start-runner
       - build-and-push-image
     runs-on: ubuntu-latest
+    env:
+      AWS_REGION: us-east-1
+    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
     steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-      - name: Initialize Docker Buildx
-        uses: docker/setup-buildx-action@v2.0.0
+      - name: Configure AWS credentials
+        uses: aws-actions/configure-aws-credentials@v1
         with:
-          install: true
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
-      - name: Tailscale
-        uses: tailscale/github-action@v1
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ env.AWS_REGION }}
+      - name: Stop EC2 runner
+        uses: philschmid/philschmid-ec2-github-runner@main
         with:
-          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
-      - name: Login to internal Container Registry
-        uses: docker/login-action@v2.1.0
-        with:
-          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
-          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
-          registry: registry.internal.huggingface.tech
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v4.3.0
-        with:
-          flavor: |
-            latest=auto
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference/sagemaker
-          tags: |
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v2
-        with:
-          context: .
-          file: Dockerfile
-          push: ${{ github.event_name != 'pull_request' }}
-          platforms: 'linux/amd64'
-          build-args: |
-            GIT_SHA={{ env.GITHUB_SHA }}
-          target: sagemaker
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
-          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=max
+          mode: stop
+          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
+          label: ${{ needs.start-runner.outputs.label }}
+          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}