misc(ci): give everything aws needs

.github/workflows/build.yaml

@@ -79,7 +79,6 @@ jobs:
                 export sccache_s3_key_prefix="trtllm"
                 export sccache_region="us-east-1"
                 export build_type="dev"
-                export is_gha_build="TRUE"
                 ;;
             rocm)
                 export dockerfile="Dockerfile_amd"
@@ -132,7 +131,6 @@ jobs:
           echo "SCCACHE_S3_KEY_PREFIX=${sccache_s3_key_prefix}" >> $GITHUB_ENV
           echo "SCCACHE_REGION=${sccache_region}" >> $GITHUB_ENV
           echo "BUILD_TYPE=${build_type}" >> $GITHUB_ENV
-          echo "IS_GHA_BUILD=${is_gha_build}" >> $GITHUB_ENV
       - name: Initialize Docker Buildx
         uses: docker/setup-buildx-action@v3
         with:
@@ -198,7 +196,7 @@ jobs:
             DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ env.LABEL }}
             PLATFORM=${{ env.PLATFORM }}
             build_type=${{ env.BUILD_TYPE }}
-            is_gha_build=${{ env.IS_GHA_BUILD }}
+            is_gha_build=true
             aws_access_key_id=${{ steps.aws-creds.outputs.aws-access-key-id }}
             aws_secret_access_key=${{ steps.aws-creds.outputs.aws-secret-access-key }}
             aws_session_token=${{ steps.aws-creds.outputs.aws-session-token }}
@@ -250,3 +248,22 @@ jobs:
           echo $DOCKER_IMAGE
           docker pull $DOCKER_IMAGE
           pytest -s -vv integration-tests ${PYTEST_FLAGS} ${EXTRA_PYTEST}
+
+  backend_trtllm_cxx_tests:
+    needs: build-and-push
+    if: needs.build-and-push.outputs.label == '-trtllm'
+    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: Run C++/CUDA tests
+        run: /usr/local/tgi/bin/tgi_trtllm_backend_tests

.github/workflows/build_trtllm.yaml

@@ -1,145 +0,0 @@
-name: Build TensorRT-LLM
-on:
-  workflow_call:
-    outputs:
-      docker_image:
-        description: "Reference to the Docker Image build by this workflow"
-        value: ${{ jobs.build-and-push.outputs.docker_image }}
-      label:
-        description: "Label generated for this build"
-        value: ${{ jobs.build-and-push.outputs.label }}
-
-jobs:
-  build-and-push:
-    permissions:
-      contents: read # Required to check out repository.
-      id-token: write # Required to authenticate via OIDC.
-
-    concurrency:
-      group: ${{ github.workflow }}-${{ github.job }}-build-and-push-${{ github.head_ref || github.run_id }}
-    outputs:
-      docker_image: ${{ steps.final.outputs.docker_image }}
-      label: ${{ steps.final.outputs.label }}
-    runs-on:
-      group: ${{ inputs.runs-on }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.pull_request.head.sha }}
-
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
-
-      - name: Extract TensorRT-LLM version
-        run: |
-          echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' $GITHUB_WORKSPACE/backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV
-          echo "TensorRT-LLM version: ${{ env.TENSORRT_LLM_VERSION }}"
-
-      - name: Set LABEL
-        run: |
-          echo "LABEL=trtllm" >> $GITHUB_ENV
-
-      - name: "Configure AWS Credentials"
-        id: aws-creds
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-region: us-east-1
-          role-to-assume: ${{ secrets.AWS_ROLE_GITHUB_TGI_TEST }}
-          role-duration-seconds: 7200
-          output-credentials: true
-
-      - name: Initialize Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          install: true
-          buildkitd-config: /tmp/buildkitd.toml
-
-      - 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
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      # If pull request
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name == 'pull_request' }}
-        id: meta-pr
-        uses: docker/metadata-action@v5
-        with:
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm
-          tags: |
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-${{ env.LABEL }}
-
-      # If main, release or tag
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name != 'pull_request' }}
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          flavor: |
-            latest=auto
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm
-          #            ghcr.io/huggingface/text-generation-inference
-          tags: |
-            type=semver,pattern={{version}}${{ env.LABEL }}
-            type=semver,pattern={{major}}.{{minor}}${{ env.LABEL }}
-            type=raw,value=latest${{ env.LABEL }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-${{ env.LABEL }}
-
-      - name: Build and push Docker image
-        id: build-and-push
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: Dockerfile_trtllm
-          target: ci-runtime
-          push: true
-          load: true
-          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
-          platforms: 'linux/amd64'
-          build-args: |
-            build_type=dev
-            is_gha_build=TRUE
-            aws_access_key_id=${{ steps.aws-creds.outputs.aws-access-key-id }}
-            aws_secret_access_key=${{ steps.aws-creds.outputs.aws-secret-access-key }}
-            aws_session_token=${{ steps.aws-creds.outputs.aws-session-token }}
-            sccache_bucket=${{ secrets.AWS_S3_BUCKET_GITHUB_TGI_TEST }}
-            sccache_s3_key_prefix=trtllm-${{ env.TENSORRT_LLM_VERSION }}
-            sccache_region=us-east-1
-          cache-from: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
-          cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
-      - name: Final
-        id: final
-        run: |
-          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: Run C++/CUDA tests
-        run: /usr/local/tgi/bin/tgi_trtllm_backend_tests
-