Implement HPUHooksInterface (#137338) #10
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: inductor | |
| on: | |
| push: | |
| branches: | |
| - main | |
| - release/* | |
| tags: | |
| - ciflow/inductor/* | |
| schedule: | |
| - cron: 29 8 * * * # about 1:29am PDT, for mem leak check and rerun disabled tests | |
| workflow_dispatch: | |
| 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: read-all | |
| 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: ${{ github.ref_type }} | |
| linux-focal-cuda12_1-py3_10-gcc9-inductor-build: | |
| name: cuda12.1-py3.10-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm86 | |
| docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9-inductor-benchmarks | |
| cuda-arch-list: '8.6' | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_distributed", shard: 1, num_shards: 1, runner: "linux.g5.12xlarge.nvidia.gpu" }, | |
| { config: "inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_timm", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_timm", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "dynamic_inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "dynamic_inductor_timm", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "dynamic_inductor_timm", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "dynamic_inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "dynamic_inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "aot_inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "aot_inductor_timm", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "aot_inductor_timm", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "aot_inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "aot_inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_cpp_wrapper", shard: 1, num_shards: 1, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| ]} | |
| secrets: inherit | |
| linux-focal-cuda12_1-py3_10-gcc9-inductor-test: | |
| name: cuda12.1-py3.10-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-focal-cuda12_1-py3_10-gcc9-inductor-build | |
| with: | |
| build-environment: linux-focal-cuda12.1-py3.10-gcc9-sm86 | |
| docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-inductor-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-inductor-build.outputs.test-matrix }} | |
| secrets: inherit | |
| linux-focal-cuda12_1-py3_12-gcc9-inductor-build: | |
| name: cuda12.1-py3.12-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| build-environment: linux-focal-cuda12.1-py3.12-gcc9-sm86 | |
| docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3.12-gcc9-inductor-benchmarks | |
| cuda-arch-list: '8.6' | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| ]} | |
| secrets: inherit | |
| linux-focal-cuda12_1-py3_12-gcc9-inductor-test: | |
| name: cuda12.1-py3.12-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-focal-cuda12_1-py3_12-gcc9-inductor-build | |
| with: | |
| build-environment: linux-focal-cuda12.1-py3.12-gcc9-sm86 | |
| docker-image: ${{ needs.linux-focal-cuda12_1-py3_12-gcc9-inductor-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-focal-cuda12_1-py3_12-gcc9-inductor-build.outputs.test-matrix }} | |
| secrets: inherit | |
| linux-jammy-cpu-py3_12-inductor-halide-build: | |
| name: linux-jammy-cpu-py3.12-gcc11-inductor-halide | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| build-environment: linux-jammy-py3.12-gcc11 | |
| docker-image-name: pytorch-linux-jammy-py3.12-halide | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor-halide", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| ]} | |
| secrets: inherit | |
| linux-jammy-cpu-py3_12-inductor-halide-test: | |
| name: linux-jammy-cpu-py3.12-gcc11-inductor-halide | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-jammy-cpu-py3_12-inductor-halide-build | |
| with: | |
| build-environment: linux-jammy-py3.12-gcc11 | |
| docker-image: ${{ needs.linux-jammy-cpu-py3_12-inductor-halide-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-jammy-cpu-py3_12-inductor-halide-build.outputs.test-matrix }} | |
| secrets: inherit | |
| linux-jammy-cpu-py3_12-inductor-triton-cpu-build: | |
| name: linux-jammy-cpu-py3.12-gcc11-inductor-triton-cpu | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| build-environment: linux-jammy-py3.12-gcc11 | |
| docker-image-name: pytorch-linux-jammy-py3.12-triton-cpu | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor-triton-cpu", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| ]} | |
| linux-jammy-cpu-py3_12-inductor-triton-cpu-test: | |
| name: linux-jammy-cpu-py3.12-gcc11-inductor-triton-cpu | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-jammy-cpu-py3_12-inductor-triton-cpu-build | |
| with: | |
| build-environment: linux-jammy-py3.12-gcc11 | |
| docker-image: ${{ needs.linux-jammy-cpu-py3_12-inductor-triton-cpu-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-jammy-cpu-py3_12-inductor-triton-cpu-build.outputs.test-matrix }} | |
| linux-focal-cuda12_4-py3_10-gcc9-inductor-build: | |
| # Should be synced with the one in inductor-periodic.yml but this only runs inductor_timm | |
| name: cuda12.4-py3.10-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| sync-tag: linux-focal-cuda12_4-py3_10-gcc9-inductor-build | |
| build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86 | |
| docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9-inductor-benchmarks | |
| cuda-arch-list: '8.6' | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor_timm", shard: 1, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| { config: "inductor_timm", shard: 2, num_shards: 2, runner: "linux.g5.4xlarge.nvidia.gpu" }, | |
| ]} | |
| secrets: inherit | |
| linux-focal-cuda12_4-py3_10-gcc9-inductor-test: | |
| name: cuda12.4-py3.10-gcc9-sm86 | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-focal-cuda12_4-py3_10-gcc9-inductor-build | |
| with: | |
| sync-tag: linux-focal-cuda12_4-py3_10-gcc9-inductor-test | |
| build-environment: linux-focal-cuda12.4-py3.10-gcc9-sm86 | |
| docker-image: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-inductor-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-inductor-build.outputs.test-matrix }} | |
| secrets: inherit | |
| linux-jammy-cpu-py3_9-gcc11-inductor-build: | |
| name: linux-jammy-cpu-py3.9-gcc11-inductor | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| build-environment: linux-jammy-py3.9-gcc11-build | |
| docker-image-name: pytorch-linux-jammy-py3.9-gcc11-inductor-benchmarks | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| test-matrix: | | |
| { include: [ | |
| { config: "inductor_avx512", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "inductor_avx512", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_timm", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_timm", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_freezing_huggingface", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_freezing_timm", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_freezing_timm", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_inductor_amp_freezing_huggingface", shard: 1, num_shards: 1, runner: "linux.16xlarge.spr" }, | |
| { config: "cpu_inductor_amp_freezing_timm", shard: 1, num_shards: 2, runner: "linux.16xlarge.spr" }, | |
| { config: "cpu_inductor_amp_freezing_timm", shard: 2, num_shards: 2, runner: "linux.16xlarge.spr" }, | |
| { config: "cpu_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.16xlarge.spr" }, | |
| { config: "cpu_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.16xlarge.spr" }, | |
| { config: "dynamic_cpu_inductor_huggingface", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_inductor_timm", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_inductor_timm", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_inductor_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_inductor_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_freezing_huggingface", shard: 1, num_shards: 1, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_freezing_timm", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_freezing_timm", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "cpu_aot_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_aot_inductor_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_aot_inductor_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_aot_inductor_amp_freezing_torchbench", shard: 1, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "dynamic_cpu_aot_inductor_amp_freezing_torchbench", shard: 2, num_shards: 2, runner: "linux.12xlarge" }, | |
| { config: "inductor_torchbench_cpu_smoketest_perf", shard: 1, num_shards: 1, runner: "linux.24xl.spr-metal" }, | |
| { config: "inductor_avx2", shard: 1, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| { config: "inductor_avx2", shard: 2, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| { config: "cpu_inductor_freezing_avx2_huggingface", shard: 1, num_shards: 1, runner: "linux.10xlarge.avx2" }, | |
| { config: "cpu_inductor_freezing_avx2_torchbench", shard: 1, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| { config: "cpu_inductor_freezing_avx2_torchbench", shard: 2, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| { config: "cpu_inductor_freezing_avx2_timm", shard: 1, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| { config: "cpu_inductor_freezing_avx2_timm", shard: 2, num_shards: 2, runner: "linux.10xlarge.avx2" }, | |
| ]} | |
| secrets: inherit | |
| linux-jammy-cpu-py3_9-gcc11-inductor-test: | |
| name: linux-jammy-cpu-py3.9-gcc11-inductor | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: linux-jammy-cpu-py3_9-gcc11-inductor-build | |
| with: | |
| build-environment: linux-jammy-py3.9-gcc11-build | |
| docker-image: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-jammy-cpu-py3_9-gcc11-inductor-build.outputs.test-matrix }} | |
| secrets: inherit |