nccl-k8s.yaml

name: NCCL on Kubernetes
on:
  schedule:
    - cron: '30 8 * * *'
  pull_request:
    types:
      - opened
      - reopened
      - ready_for_review
      - synchronize
    paths-ignore:
      - '**.md'
  workflow_dispatch:
    inputs:
      # Note that cuda-dl-base installs the NCCL tests, while the vanilla nvidia/cuda
      # images do not; when JAX-Toolbox moves to using cuda-dl-base this workflow ought
      # to be modified to test one of the JAX-Toolbox containers.
      CONTAINER:
        type: string
        description: Container to test, this is assumed to already contain the NCCL tests e.g. cuda-dl-base or derived
        default: ''
        required: false

concurrency:
  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

permissions:
  actions:  write # to cancel previous workflows
  contents: read  # to fetch code
  packages: write # to upload container

jobs:
  nccl-tests:
    uses: ./.github/workflows/_test_nccl.yaml
    with:
      CONTAINER: ${{ inputs.CONTAINER || 'nvcr.io/nvidia/cuda-dl-base:24.12-cuda12.6-devel-ubuntu24.04' }}
    secrets: inherit