Geo Min
f9a957bbab
* First commit for rccl multi node test workflow * Adding workflow dispatch * Added branch based pull trigger * Changed typo in branch name * Add input variables to push * Removed input variables to push * Added self hosted runner for Vultr cloud * Skipping build and only running test * Changed test runner label name * Made changes to executable paths in test script * Made changes to run * Made changes to cd into cvs dir * This is a dummy commit * Added cmake options * Modified build options * Commiting build changes * Adding rccl and rccl-tests * Re-ordering rccl and rccl-tests * adding --global command * modified cmake command * modified script paths * Testing OIDC for rccl repo * Testing OIDC for rccl repo * Testing build and upload workflow * use default env variable for AMDGPU families on push workflow trigger * Adding cleanup and correct role * Adding additional yml files * Fixing typo'; * Adding new sha * Adding correct gpu target * Adding back venv bin activate * Adding workflow dispatch for tests * Testing * Adding cat * Adding cat * Adding rocm dir change * Adding checkout * cat with sudo * rccl checkout * correcting branch * removing sudo * trying to adjust correct path' * Adding output dir path * Use docker container with pre-installed MPI * Adding back build steps * Fixing SHA * Adding exclusion logic: * Adding test * Adding CI check * Removing testing * Limit to build only rccl, rccl-tests and required dependencies * Adding test * Removing test * Removing quote * Reverting test * PR comments --------- Co-authored-by: arravikum <arravikum@amd.com> Co-authored-by: Marius Brehler <marius.brehler@amd.com>
59 righe
1.8 KiB
YAML
59 righe
1.8 KiB
YAML
name: TheRock Test Packages
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
amdgpu_families:
|
|
type: string
|
|
test_runs_on:
|
|
type: string
|
|
artifact_run_id:
|
|
type: string
|
|
workflow_dispatch:
|
|
inputs:
|
|
amdgpu_families:
|
|
type: string
|
|
test_runs_on:
|
|
type: string
|
|
artifact_run_id:
|
|
type: string
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
jobs:
|
|
test_rccl:
|
|
name: 'Test'
|
|
runs-on: ${{ inputs.test_runs_on }}
|
|
defaults:
|
|
run:
|
|
shell: bash
|
|
env:
|
|
VENV_DIR: ${{ github.workspace }}/.venv
|
|
ARTIFACT_RUN_ID: "${{ inputs.artifact_run_id }}"
|
|
OUTPUT_ARTIFACTS_DIR: /home/arravikum/dist_new/dist/rocm
|
|
THEROCK_BIN_DIR: "./build/bin"
|
|
steps:
|
|
- name: Checkout Repository
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
|
with:
|
|
repository: "ROCm/TheRock"
|
|
ref: 890c856134d955441790c8ed2d60ad4fb027f4e5
|
|
|
|
- name: Run setup test environment workflow
|
|
uses: './.github/actions/setup_test_environment'
|
|
with:
|
|
ARTIFACT_RUN_ID: ${{ env.ARTIFACT_RUN_ID }}
|
|
AMDGPU_FAMILIES: ${{ inputs.amdgpu_families }}
|
|
OUTPUT_ARTIFACTS_DIR: ${{ env.OUTPUT_ARTIFACTS_DIR }}
|
|
VENV_DIR: ${{ env.VENV_DIR }}
|
|
FETCH_ARTIFACT_ARGS: "--rccl"
|
|
IS_PR_FROM_FORK: ${{ github.event.pull_request.head.repo.fork }}
|
|
|
|
- name: Run tests on vultr-linux-node
|
|
run: |
|
|
source /home/arravikum/TheRock/.venv/bin/activate
|
|
cd /home/arravikum/cvs
|
|
pytest -vvv --log-file=/tmp/rccl_log.log -s ./tests/rccl/rccl_multinode_cvs.py --cluster_file ./input/cluster.json --config_file ./input/mi300_config.json --html=/var/www/html/cvs/ci_test_report.html --capture=tee-sys --self-contained-html
|
|
|