misc(ci): wtfinfini

.github/workflows/build_trtllm.yaml

@@ -16,7 +16,7 @@ on:
         value: ${{ jobs.build-and-push.outputs.label }}
 
 jobs:
-  build-trtllm-and-push:
+  build-and-push:
     permissions:
       contents: read # Required to check out repository.
       id-token: write # Required to authenticate via OIDC.
@@ -131,4 +131,28 @@ jobs:
           echo "docker_image=registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm:sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
           echo "label=${{ env.LABEL }}" >> "$GITHUB_OUTPUT"
 
+  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-g6-12xl-plus-priv-cache
+    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: whoami
+        run: |
+          echo "Container: ${{ needs.build-and-push.outputs.docker_image }}"
+
+      - name: List binaries
+        run: ls -alh /usr/local/tgi
+
+      - name: Run C++/CUDA tests
+        run: /usr/local/tgi/bin/tgi_trtllm_backend_tests
 

.github/workflows/trtllm_tests.yaml

@@ -1,56 +0,0 @@
-name: "TensorRT-LLM C/C++/CUDA Test Suite"
-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-backend:
-    permissions:
-      contents: write
-      packages: write
-      id-token: write
-    uses: ./.github/workflows/build_trtllm.yaml
-    with:
-      runs-on: aws-highmemory-64-plus-priv
-    secrets: inherit
-
-  run-tests:
-    needs: build-backend
-    concurrency:
-      group: ${{ github.workflow }}-${{ github.job }}-trtllm-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    runs-on:
-      group: aws-g6-12xl-plus-priv-cache
-    container:
-      image: ${{ needs.build-backend.outputs.docker_image }}
-      credentials:
-        username: ${{ secrets.REGISTRY_USERNAME }}
-        password: ${{ secrets.REGISTRY_PASSWORD }}
-      options: --gpus all --shm-size=8g
-
-    steps:
-      - name: whoami
-        run: |
-          echo "Container: ${{ needs.build-backend.outputs.docker_image }}"
-      - name: List binaries
-        run: ls -alh /usr/local/tgi
-
-      - name: Run C++/CUDA tests
-        run: /usr/local/tgi/bin/tgi_trtllm_backend_tests