Enable MLflow tracking from MLFLOW_TRACKING_URI as well as --mlflow #6270
Workflow file for this run
This file contains hidden or 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: Example tests | |
| on: | |
| push: | |
| branches: ["pull-request/[0-9]+"] | |
| # NOTE: paths cannot be used since push happens to copied PR and only latest commit to PR is used | |
| schedule: | |
| - cron: "0 0 * * *" # Nightly | |
| workflow_dispatch: | |
| # On-demand | |
| concurrency: | |
| # Cancel previous runs if new commit is pushed to the same PR | |
| group: ${{ github.workflow }}-${{ startsWith(github.ref, 'refs/heads/pull-request/') && github.ref || github.sha }} | |
| cancel-in-progress: true | |
| # Each job's `allow_failure` reads the repo variable ALLOW_FAILURE_EXAMPLE_TESTS: | |
| # a comma-separated list of example names whose test failures should be non-blocking, e.g. "torch_trt,llm_qat" | |
| jobs: | |
| pr-gate: | |
| uses: ./.github/workflows/_pr_gate.yml | |
| permissions: | |
| checks: read | |
| secrets: inherit | |
| with: | |
| files: | | |
| .github/actions/cache-extensions/** | |
| .github/workflows/_example_tests_runner.yml | |
| .github/workflows/example_tests.yml | |
| examples/** | |
| modelopt/** | |
| pyproject.toml | |
| tests/examples/** | |
| ##### PyTorch Example Tests (speculative_decoding requires 26.01 image) ##### | |
| torch: | |
| needs: [pr-gate] | |
| if: needs.pr-gate.outputs.any_changed == 'true' | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| example: [gpt-oss, llm_distill, llm_qat, llm_sparsity, specdec_bench] | |
| include: | |
| - example: speculative_decoding | |
| docker_image: "26.01" | |
| uses: ./.github/workflows/_example_tests_runner.yml | |
| permissions: | |
| contents: read | |
| secrets: inherit | |
| with: | |
| docker_image: "nvcr.io/nvidia/pytorch:${{ matrix.docker_image || '26.06' }}-py3" | |
| example: ${{ matrix.example }} | |
| timeout_minutes: 30 | |
| pip_install_extras: "[hf,dev-test]" | |
| runner: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }} | |
| allow_failure: ${{ contains(format(',{0},', vars.ALLOW_FAILURE_EXAMPLE_TESTS), format(',{0},', matrix.example)) }} | |
| ##### TensorRT-LLM Example Tests (pr/non-pr split: non-pr runs extra eval examples) ##### | |
| trtllm-pr: | |
| needs: [pr-gate] | |
| if: startsWith(github.ref, 'refs/heads/pull-request/') && needs.pr-gate.outputs.any_changed == 'true' | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| example: [hf_ptq] | |
| uses: ./.github/workflows/_example_tests_runner.yml | |
| permissions: | |
| contents: read | |
| secrets: inherit | |
| with: | |
| docker_image: "nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc20" | |
| example: ${{ matrix.example }} | |
| pip_install_extras: "[hf,dev-test]" | |
| runner: linux-amd64-gpu-rtxpro6000-latest-1 | |
| allow_failure: ${{ contains(format(',{0},', vars.ALLOW_FAILURE_EXAMPLE_TESTS), format(',{0},', matrix.example)) }} | |
| trtllm-non-pr: | |
| if: ${{ !startsWith(github.ref, 'refs/heads/pull-request/') }} | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| example: [llm_eval, hf_ptq] | |
| uses: ./.github/workflows/_example_tests_runner.yml | |
| permissions: | |
| contents: read | |
| secrets: inherit | |
| with: | |
| docker_image: "nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc20" | |
| example: ${{ matrix.example }} | |
| pip_install_extras: "[hf,dev-test]" | |
| runner: linux-amd64-gpu-rtxpro6000-latest-2 | |
| allow_failure: ${{ contains(format(',{0},', vars.ALLOW_FAILURE_EXAMPLE_TESTS), format(',{0},', matrix.example)) }} | |
| ##### Megatron Example Tests ##### | |
| megatron: | |
| needs: [pr-gate] | |
| if: needs.pr-gate.outputs.any_changed == 'true' | |
| uses: ./.github/workflows/_example_tests_runner.yml | |
| permissions: | |
| contents: read | |
| secrets: inherit | |
| with: | |
| docker_image: "nvcr.io/nvidia/nemo:26.06" | |
| example: megatron_bridge | |
| timeout_minutes: 60 | |
| pip_install_extras: "[hf,puzzletron,dev-test]" | |
| runner: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }} | |
| allow_failure: ${{ contains(format(',{0},', vars.ALLOW_FAILURE_EXAMPLE_TESTS), ',megatron_bridge,') }} | |
| ##### ONNX/TensorRT Example Tests ##### | |
| onnx: | |
| needs: [pr-gate] | |
| if: needs.pr-gate.outputs.any_changed == 'true' | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| example: [diffusers, torch_onnx, torch_trt] | |
| uses: ./.github/workflows/_example_tests_runner.yml | |
| permissions: | |
| contents: read | |
| secrets: inherit | |
| with: | |
| # Pinned to 26.05 (TensorRT 10): torch-tensorrt is capped at <2.13 (== 2.12.1), | |
| # which needs libnvinfer.so.10; newer tensorrt containers drop it. Bump only once | |
| # a torch-tensorrt build for the newer TensorRT is available. | |
| docker_image: "nvcr.io/nvidia/tensorrt:26.05-py3" | |
| example: ${{ matrix.example }} | |
| timeout_minutes: 45 | |
| pip_install_extras: "[onnx,hf,dev-test]" | |
| runner: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }} | |
| allow_failure: ${{ contains(format(',{0},', vars.ALLOW_FAILURE_EXAMPLE_TESTS), format(',{0},', matrix.example)) }} | |
| ##### Required Check for PR ##### | |
| example-pr-required-check: | |
| # Run even if example tests are skipped | |
| if: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && always() }} | |
| needs: [pr-gate, torch, trtllm-pr, megatron, onnx] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Required example tests did not succeed | |
| if: | | |
| needs.pr-gate.result != 'success' || | |
| (needs.pr-gate.outputs.any_changed == 'true' && ( | |
| needs.torch.result != 'success' || | |
| needs.trtllm-pr.result != 'success' || | |
| needs.megatron.result != 'success' || | |
| needs.onnx.result != 'success' | |
| )) | |
| run: exit 1 |