vllm-test #41
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: vllm-test | |
| on: | |
| push: | |
| branches: | |
| - main | |
| - release/* | |
| tags: | |
| - ciflow/vllm/* | |
| workflow_dispatch: | |
| schedule: | |
| - cron: '0 */8 * * *' # every 8 hours at minute 0 (UTC) | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref_name }}-${{ github.ref_type == 'branch' && github.sha }}-${{ github.event_name == 'workflow_dispatch' }} | |
| cancel-in-progress: true | |
| permissions: | |
| id-token: write | |
| contents: read | |
| jobs: | |
| get-label-type: | |
| name: get-label-type | |
| uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main | |
| if: ${{ (github.event_name != 'schedule' || github.repository == 'pytorch/pytorch') && github.repository_owner == 'pytorch' }} | |
| with: | |
| triggering_actor: ${{ github.triggering_actor }} | |
| issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }} | |
| curr_branch: ${{ github.head_ref || github.ref_name }} | |
| curr_ref_type: ${{ github.ref_type }} | |
| opt_out_experiments: lf | |
| torch-build: | |
| name: ci-vllm-test | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| # When building vLLM, uv doesn't like that we rename wheel without changing the wheel metadata | |
| allow-reuse-old-whl: false | |
| build-additional-packages: "vision audio" | |
| build-external-packages: "vllm" | |
| build-environment: linux-jammy-cuda12.8-py3.12-gcc11 | |
| docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3.12-gcc11-vllm | |
| cuda-arch-list: '8.0;8.9;9.0' | |
| runner: linux.24xlarge.memory | |
| test-matrix: | | |
| { include: [ | |
| { config: "vllm_basic_correctness_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_basic_models_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_entrypoints_test", shard: 1, num_shards: 1,runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_regression_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_multi_model_processor_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_pytorch_compilation_unit_tests", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_28_failure_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_multi_model_test_28_failure_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu"}, | |
| { config: "vllm_languagde_model_test_extended_generation_28_failure_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu"}, | |
| { config: "vllm_distributed_test_2_gpu_28_failure_test", shard: 1, num_shards: 1, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_test", shard: 0, num_shards: 4, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_test", shard: 1, num_shards: 4, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_test", shard: 2, num_shards: 4, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_test", shard: 3, num_shards: 4, runner: "linux.g6.4xlarge.experimental.nvidia.gpu" }, | |
| { config: "vllm_lora_tp_test_distributed", shard: 1, num_shards: 1, runner: "linux.g6.12xlarge.nvidia.gpu"}, | |
| { config: "vllm_distributed_test_28_failure_test", shard: 1, num_shards: 1, runner: "linux.g6.12xlarge.nvidia.gpu"} | |
| ]} | |
| secrets: inherit | |
| vllm-test-sm89: | |
| name: ci-vllm-test | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: [ | |
| torch-build, | |
| ] | |
| with: | |
| build-environment: linux-jammy-cuda12.8-py3.12-gcc11 | |
| docker-image: ${{ needs.torch-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.torch-build.outputs.test-matrix }} | |
| secrets: inherit |