Merge pull request #368 from huggingface/add_cuda_ci

Adding cuda CI

.github/workflows/ci_cuda.yaml

@@ -0,0 +1,87 @@
+name: CI / cuda
+
+on:
+  workflow_dispatch:
+  pull_request:
+
+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.xlarge
+      EC2_SUBNET_ID: subnet-931b34f5,subnet-ecb993cd,subnet-943dc2d8,subnet-45371f1a,subnet-ee93e0df,subnet-fddc3dfc
+      EC2_SECURITY_GROUP: sg-030175c435ac141d6
+    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 }}"}
+            ]
+
+  test-cuda:
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
+      cancel-in-progress: true
+    needs: start-runner # required to start the main job when the runner is ready
+    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
+    permissions:
+      contents: write
+      packages: write
+      # This is used to complete the identity challenge
+      # with sigstore/fulcio when running outside of PRs.
+      id-token: write
+      security-events: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Install Rust Stable
+        run: curl https://sh.rustup.rs -sSf | sh -s -- -y
+      - uses: Swatinem/rust-cache@v2
+      - run: apt update -y && apt install libssl-dev -y
+      - name: Test (cuda)
+        run: PATH=$PATH:/usr/local/cuda-11.8/bin/ /root/.cargo/bin/cargo test --features cuda
+  stop-runner:
+    name: Stop self-hosted EC2 runner
+    needs:
+      - start-runner
+      - test-cuda
+    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: 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: Stop EC2 runner
+        uses: philschmid/philschmid-ec2-github-runner@main
+        with:
+          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 }}