mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 12:54:11 +08:00
1. Run distributed job with B200 runner, periodically. 2. discovered generic distributed test issue that certain unit test hard-coded ranks, calling for require_exact_world_size(world_size) API instead of require_world_size(world_size). Pull Request resolved: https://github.com/pytorch/pytorch/pull/159323 Approved by: https://github.com/eqy Co-authored-by: Aidyn-A <aidyn.b.aitzhan@gmail.com>
63 lines
2.3 KiB
YAML
63 lines
2.3 KiB
YAML
name: CI for distributed tests on B200
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- .github/workflows/b200-distributed.yml
|
|
workflow_dispatch:
|
|
push:
|
|
tags:
|
|
- ciflow/b200-distributed/*
|
|
schedule:
|
|
- cron: 46 8 * * * # about 1:46am PDT
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }}
|
|
cancel-in-progress: true
|
|
|
|
permissions:
|
|
id-token: write
|
|
contents: read
|
|
|
|
jobs:
|
|
|
|
get-label-type:
|
|
if: github.repository_owner == 'pytorch'
|
|
name: get-label-type
|
|
uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main
|
|
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: ${{ github.ref_type }}
|
|
|
|
linux-jammy-cuda12_8-py3_10-gcc11-build-distributed-b200:
|
|
name: linux-jammy-cuda12.8-py3.10-gcc11-build-distributed-b200
|
|
uses: ./.github/workflows/_linux-build.yml
|
|
needs: get-label-type
|
|
with:
|
|
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
|
|
runner: linux.12xlarge.memory
|
|
build-environment: linux-jammy-cuda12.8-py3.10-gcc11-distributed-b200
|
|
docker-image-name: ci-image:pytorch-linux-jammy-cuda12.8-cudnn9-py3-gcc11
|
|
cuda-arch-list: '10.0'
|
|
test-matrix: |
|
|
{ include: [
|
|
{ config: "distributed", shard: 1, num_shards: 2, runner: "linux.dgx.b200.8" },
|
|
{ config: "distributed", shard: 2, num_shards: 2, runner: "linux.dgx.b200.8" },
|
|
]}
|
|
secrets: inherit
|
|
|
|
linux-jammy-cuda12_8-py3_10-gcc11-test-distributed-b200:
|
|
name: linux-jammy-cuda12.8-py3.10-gcc11-test-b200
|
|
uses: ./.github/workflows/_linux-test.yml
|
|
needs:
|
|
- linux-jammy-cuda12_8-py3_10-gcc11-build-distributed-b200
|
|
with:
|
|
timeout-minutes: 1200
|
|
build-environment: linux-jammy-cuda12.8-py3.10-gcc11-distributed-b200
|
|
docker-image: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build-distributed-b200.outputs.docker-image }}
|
|
test-matrix: ${{ needs.linux-jammy-cuda12_8-py3_10-gcc11-build-distributed-b200.outputs.test-matrix }}
|
|
aws-role-to-assume: arn:aws:iam::308535385114:role/gha_workflow_s3_and_ecr_read_only
|
|
secrets: inherit
|