Create test-trtllm.yml

.github/workflows/test-trtllm.yml

@@ -0,0 +1,50 @@
+name: "TensorRT-LLM C/C++/CUDA Test Suite POPO"
+on:
+  push:
+    branches:
+      - 'main'
+      - 'trtllm/ci'
+    tags:
+      - 'v*'
+  pull_request:
+    paths:
+      - "backends/trtllm"
+      - "server/**"
+      - "proto/**"
+      - "router/**"
+      - "launcher/**"
+      - "Cargo.lock"
+      - "rust-toolchain.toml"
+      - ".github/workflows/build_trtllm.yaml"
+      - ".github/workflows/trtllm_tests.yaml"
+    branches:
+      - "main"
+
+jobs:
+  build-and-push:
+    permissions:
+      contents: write
+      packages: write
+      id-token: write
+    uses: ./.github/workflows/build_trtllm.yaml
+    with:
+      runs-on: aws-highmemory-64-plus-priv
+    secrets:
+        AWS_ROLE_GITHUB_TGI_TEST: ${{ secrets.AWS_ROLE_GITHUB_TGI_TEST }}
+  run-tests:
+    needs: build-and-push
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.job }}-trtllm-${{ github.head_ref || github.run_id }}
+      cancel-in-progress: true
+    runs-on:
+      group: aws-highmemory-64-plus-priv
+    container:
+      image: ${{ needs.build-and-push.outputs.docker_image }}
+      credentials:
+        username: ${{ secrets.REGISTRY_USERNAME }}
+        password: ${{ secrets.REGISTRY_PASSWORD }}
+      options: --gpus all --shm-size=8g
+
+    steps:
+      - name: Run C++/CUDA tests
+        run: /usr/local/tgi/bin/tgi_trtllm_backend_tests