diff --git a/.github/workflows/build_trtllm.yaml b/.github/workflows/build_trtllm.yaml index be9019ce..3c11fe52 100644 --- a/.github/workflows/build_trtllm.yaml +++ b/.github/workflows/build_trtllm.yaml @@ -119,15 +119,16 @@ jobs: 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=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min tests: + needs: build runs-on: group: aws-g6-12xl-plus-priv-cache - container: - image: - registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm:${{ env.LABEL }} - credentials: - username: ${{ secrets.REGISTRY_USERNAME }} - password: ${{ secrets.REGISTRY_PASSWORD }} - options: --gpus all --net=host + container: + image: + registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm:${{ env.LABEL }} + credentials: + username: ${{ secrets.REGISTRY_USERNAME }} + password: ${{ secrets.REGISTRY_PASSWORD }} + options: --gpus all --net=host steps: - name: Run C++/CUDA tests