mirror of
https://github.com/zebrajr/pytorch.git
synced 2026-01-15 12:15:51 +00:00
49f600e864
Autorevert can issue multiple dispatches without waiting for the last one to finish: https://github.com/pytorch/pytorch/actions/workflows/pull.yml?query=branch%3Atrunk%2Faadd016020d718ae862361d23d98f61a5e6e3903 (this is expected behavior in certain cases, e.g. the specific job was already finished, but not the whole workflow) But currently in pytorch workflows the concurrency policy cancels concurrent workflow runs, even if they are dispatches. This PR: 1. removes the limit for dispatches (for the workflows that are monitored by autorevert). Note: there is still a hard cap for the total number of dispatches on autorevert side. 2. adds logging, so in the future we can change the concurrency to apply only to autorevert dispatches (we'll know what correct `actor` value to use) 3. removes garbage from the key in linux-aarch64.yml wf ---- Testing: see my two manual concurrent dispatches here: https://github.com/pytorch/pytorch/actions/workflows/pull.yml?query=branch%3Aunlimited-dispatches++ (also notice that concurrency correctly cancels wf on PR update) new logging: https://github.com/pytorch/pytorch/actions/runs/20444849087/job/58745963215#step:2:20 Pull Request resolved: https://github.com/pytorch/pytorch/pull/171132 Approved by: https://github.com/clee2000, https://github.com/jeanschmidt
83 lines
3.1 KiB
YAML
83 lines
3.1 KiB
YAML
name: periodic-rocm-mi300
|
|
|
|
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/*
|
|
- ciflow/periodic-rocm-mi300/*
|
|
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.run_id }}-${{ github.event_name == 'schedule' }}-${{ 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: ${{ github.ref_type }}
|
|
|
|
linux-noble-rocm-py3_12-build:
|
|
name: linux-noble-rocm-py3.12-mi300
|
|
uses: ./.github/workflows/_linux-build.yml
|
|
needs: get-label-type
|
|
with:
|
|
runner_prefix: "${{ needs.get-label-type.outputs.label-type }}"
|
|
build-environment: linux-noble-rocm-py3.12-mi300
|
|
docker-image-name: ci-image:pytorch-linux-noble-rocm-n-py3
|
|
test-matrix: |
|
|
{ include: [
|
|
{ config: "distributed", shard: 1, num_shards: 3, runner: "linux.rocm.gpu.gfx942.4.b", owners: ["module:rocm", "oncall:distributed"] },
|
|
{ config: "distributed", shard: 2, num_shards: 3, runner: "linux.rocm.gpu.gfx942.4.b", owners: ["module:rocm", "oncall:distributed"] },
|
|
{ config: "distributed", shard: 3, num_shards: 3, runner: "linux.rocm.gpu.gfx942.4.b", owners: ["module:rocm", "oncall:distributed"] },
|
|
]}
|
|
secrets: inherit
|
|
|
|
linux-noble-rocm-py3_12-test:
|
|
permissions:
|
|
id-token: write
|
|
contents: read
|
|
name: linux-noble-rocm-py3.12-mi300
|
|
uses: ./.github/workflows/_rocm-test.yml
|
|
needs:
|
|
- linux-noble-rocm-py3_12-build
|
|
- target-determination
|
|
with:
|
|
build-environment: ${{ needs.linux-noble-rocm-py3_12-build.outputs.build-environment }}
|
|
docker-image: ${{ needs.linux-noble-rocm-py3_12-build.outputs.docker-image }}
|
|
test-matrix: ${{ needs.linux-noble-rocm-py3_12-build.outputs.test-matrix }}
|
|
secrets: inherit
|