periodic #213
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: periodic | |
on: | |
schedule: | |
# We have several schedules so jobs can check github.event.schedule to activate only for a fraction of the runs. | |
# Also run less frequently on weekends. | |
- cron: 45 0,8,16 * * 1-5 | |
- cron: 45 4 * * 0,6 | |
- cron: 45 4,12,20 * * 1-5 | |
- cron: 45 12 * * 0,6 | |
- cron: 29 8 * * * # about 1:29am PDT, for mem leak check and rerun disabled tests | |
push: | |
tags: | |
- ciflow/periodic/* | |
branches: | |
- release/* | |
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' }}-${{ github.event_name == 'schedule' }}-${{ github.event.schedule }} | |
cancel-in-progress: true | |
permissions: read-all | |
jobs: | |
llm-td: | |
if: github.repository_owner == 'pytorch' | |
name: before-test | |
uses: ./.github/workflows/llm_td_retrieval.yml | |
permissions: | |
id-token: write | |
contents: read | |
target-determination: | |
name: before-test | |
uses: ./.github/workflows/target_determination.yml | |
needs: llm-td | |
permissions: | |
id-token: write | |
contents: read | |
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: ${{ github.ref_type }} | |
linux-focal-cuda12_1-py3_10-gcc9-build: | |
name: linux-focal-cuda12.1-py3.10-gcc9 | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-cuda12.1-py3.10-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9 | |
test-matrix: | | |
{ include: [ | |
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
]} | |
secrets: inherit | |
linux-focal-cuda12_1-py3_10-gcc9-test: | |
name: linux-focal-cuda12.1-py3.10-gcc9 | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda12_1-py3_10-gcc9-build | |
- target-determination | |
with: | |
build-environment: linux-focal-cuda12.1-py3.10-gcc9 | |
docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda12_4-py3_10-gcc9-build: | |
name: linux-focal-cuda12.4-py3.10-gcc9 | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-cuda12.4-py3.10-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9 | |
test-matrix: | | |
{ include: [ | |
{ config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
{ config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
{ config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
{ config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
{ config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
]} | |
secrets: inherit | |
linux-focal-cuda12_4-py3_10-gcc9-test: | |
name: linux-focal-cuda12.4-py3.10-gcc9 | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda12_4-py3_10-gcc9-build | |
- target-determination | |
with: | |
timeout-minutes: 360 | |
build-environment: linux-focal-cuda12.4-py3.10-gcc9 | |
docker-image: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda12_4-py3_10-gcc9-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_9-gcc9-build: | |
name: linux-focal-cuda11.8-py3.9-gcc9 | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-cuda11.8-py3.9-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9 | |
cuda-arch-list: 8.6 | |
test-matrix: | | |
{ include: [ | |
{ config: "multigpu", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] }, | |
]} | |
build-with-debug: false | |
secrets: inherit | |
linux-focal-cuda11_8-py3_9-gcc9-test: | |
name: linux-focal-cuda11.8-py3.9-gcc9 | |
uses: ./.github/workflows/_linux-test.yml | |
needs: linux-focal-cuda11_8-py3_9-gcc9-build | |
with: | |
build-environment: linux-focal-cuda11.8-py3.9-gcc9 | |
docker-image: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_10-gcc9-debug-build: | |
name: linux-focal-cuda11.8-py3.10-gcc9-debug | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-cuda11.8-py3.10-gcc9-debug | |
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9 | |
build-with-debug: true | |
test-matrix: | | |
{ include: [ | |
{ config: "default", shard: 1, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] }, | |
{ config: "default", shard: 2, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] }, | |
{ config: "default", shard: 3, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] }, | |
{ config: "default", shard: 4, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] }, | |
{ config: "default", shard: 5, num_shards: 5, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu", owners: ["oncall:debug-build"] }, | |
]} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_10-gcc9-debug-test: | |
name: linux-focal-cuda11.8-py3.10-gcc9-debug | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda11_8-py3_10-gcc9-debug-build | |
- target-determination | |
with: | |
build-environment: linux-focal-cuda11.8-py3.10-gcc9-debug | |
docker-image: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-debug-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-debug-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-rocm6_2-py3_10-build: | |
name: linux-focal-rocm6.2-py3.10 | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-rocm6.2-py3.10 | |
docker-image-name: pytorch-linux-focal-rocm-n-py3 | |
test-matrix: | | |
{ include: [ | |
{ config: "distributed", shard: 1, num_shards: 3, runner: "linux.rocm.gpu", owners: ["module:rocm", "oncall:distributed"] }, | |
{ config: "distributed", shard: 2, num_shards: 3, runner: "linux.rocm.gpu", owners: ["module:rocm", "oncall:distributed"] }, | |
{ config: "distributed", shard: 3, num_shards: 3, runner: "linux.rocm.gpu", owners: ["module:rocm", "oncall:distributed"] }, | |
]} | |
secrets: inherit | |
linux-focal-rocm6_2-py3_10-test: | |
permissions: | |
id-token: write | |
contents: read | |
name: linux-focal-rocm6.2-py3.10 | |
uses: ./.github/workflows/_rocm-test.yml | |
needs: | |
- linux-focal-rocm6_2-py3_10-build | |
- target-determination | |
with: | |
build-environment: linux-focal-rocm6.2-py3.10 | |
docker-image: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-rocm6_2-py3_10-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build: | |
name: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
if: false # See https://github.com/pytorch/pytorch/issues/138750 | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
use_split_build: true | |
build-environment: linux-focal-cuda12.1-py3.10-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9 | |
test-matrix: | | |
{ include: [ | |
{ config: "nogpu_AVX512", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_AVX512", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 1, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "nogpu_NO_AVX2", shard: 2, num_shards: 2, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge" }, | |
{ config: "jit_legacy", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
]} | |
secrets: inherit | |
linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build-test: | |
name: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build | |
- target-determination | |
with: | |
build-environment: linux-focal-cuda12.1-py3.10-gcc9-experimental-split-build | |
docker-image: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda12_1-py3_10-gcc9-experimental-split-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build: | |
name: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
if: false # See https://github.com/pytorch/pytorch/issues/138750 | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
use_split_build: true | |
build-environment: linux-focal-cuda11.8-py3.9-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9 | |
cuda-arch-list: 8.6 | |
test-matrix: | | |
{ include: [ | |
{ config: "multigpu", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g5.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] }, | |
]} | |
build-with-debug: false | |
secrets: inherit | |
linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build-test: | |
name: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build-test | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build | |
- target-determination | |
with: | |
build-environment: linux-focal-cuda11.8-py3.9-gcc9-experimental-split-build | |
docker-image: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_9-gcc9-experimental-split-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build: | |
name: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
if: false # See https://github.com/pytorch/pytorch/issues/138750 | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
use_split_build: true | |
build-environment: linux-focal-cuda11.8-py3.10-gcc9 | |
docker-image-name: pytorch-linux-focal-cuda11.8-cudnn9-py3-gcc9 | |
cuda-arch-list: '7.5' | |
test-matrix: | | |
{ include: [ | |
{ config: "distributed", shard: 1, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] }, | |
{ config: "distributed", shard: 2, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] }, | |
{ config: "distributed", shard: 3, num_shards: 3, runner: "${{ needs.get-label-type.outputs.label-type }}linux.g4dn.12xlarge.nvidia.gpu", owners: ["oncall:distributed"] }, | |
]} | |
secrets: inherit | |
linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build-test: | |
name: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build-test | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build | |
- target-determination | |
with: | |
timeout-minutes: 360 | |
build-environment: linux-focal-cuda11.8-py3.10-gcc9-experimental-split-build | |
docker-image: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda11_8-py3_10-gcc9-experimental-split-build.outputs.test-matrix }} | |
secrets: inherit | |
linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build: | |
name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck | |
uses: ./.github/workflows/_linux-build.yml | |
needs: get-label-type | |
with: | |
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
build-environment: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck | |
docker-image-name: pytorch-linux-focal-cuda12.1-cudnn9-py3-gcc9 | |
cuda-arch-list: 8.6 | |
test-matrix: | | |
{ include: [ | |
{ config: "default", shard: 1, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 2, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 3, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 4, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 5, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 6, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 7, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
{ config: "default", shard: 8, num_shards: 8, runner: "linux.g5.4xlarge.nvidia.gpu", owners: ["module:slowgradcheck"] }, | |
]} | |
secrets: inherit | |
linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-test: | |
name: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck | |
uses: ./.github/workflows/_linux-test.yml | |
needs: | |
- linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build | |
- target-determination | |
with: | |
build-environment: linux-focal-cuda12.1-py3-gcc9-slow-gradcheck | |
docker-image: ${{ needs.linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build.outputs.docker-image }} | |
test-matrix: ${{ needs.linux-focal-cuda12_1-py3-gcc9-slow-gradcheck-build.outputs.test-matrix }} | |
timeout-minutes: 300 | |
secrets: inherit | |
linux-focal-cuda12_4-py3_10-gcc9-bazel-test: | |
name: linux-focal-cuda12.4-py3.10-gcc9-bazel-test | |
uses: ./.github/workflows/_bazel-build-test.yml | |
needs: get-label-type | |
with: | |
runner: "${{ needs.get-label-type.outputs.label-type }}linux.large" | |
build-environment: linux-focal-cuda12.4-py3.10-gcc9-bazel-test | |
docker-image-name: pytorch-linux-focal-cuda12.4-cudnn9-py3-gcc9 | |
cuda-version: "12.4" | |
test-matrix: | | |
{ include: [ | |
{ config: "default", shard: 1, num_shards: 1, runner: "${{ needs.get-label-type.outputs.label-type }}linux.4xlarge.nvidia.gpu" }, | |
]} | |
secrets: inherit |