change runner size #70
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Build TensorRT-LLM | ||
| on: | ||
| push: | ||
| branches: | ||
| - 'main' | ||
| - 'trtllm/ci' | ||
| tags: | ||
| - 'v*' | ||
| pull_request: | ||
| paths: | ||
| - "backends/trtllm" | ||
| - "server/**" | ||
| - "proto/**" | ||
| - "router/**" | ||
| - "launcher/**" | ||
| - "Cargo.lock" | ||
| - "rust-toolchain.toml" | ||
| branches: | ||
| - "main" | ||
| permissions: | ||
| contents: read # Required to check out repository. | ||
| id-token: write # Required to authenticate via OIDC. | ||
| jobs: | ||
| build: | ||
| runs-on: | ||
| group: aws-highmemory-64-plus-priv | ||
| steps: | ||
| - uses: actions/checkout@v4 | ||
| - 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: "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 | ||
| env: | ||
| LABEL: "trtllm" | ||
| 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 | ||
| 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 }} | ||
|
Check failure on line 127 in .github/workflows/build_trtllm.yaml
|
||
| credentials: | ||
| username: ${{ secrets.REGISTRY_USERNAME }} | ||
| password: ${{ secrets.REGISTRY_PASSWORD }} | ||
| options: --gpus all --net=host | ||
| steps: | ||
| - name: Run C++/CUDA tests | ||
| run: /usr/local/tgi/tgi_trtllm_backend_tests | ||
