[AMD][CI] Swap the AMD PR gate to ROCm 7.2 and demote ROCm 7.0 to a daily shadow (#34204)

Co-authored-by: yctseng0211 <yctseng@smci355-ccs-aus-m12-17.cs-aus.dcgpu>
Co-authored-by: Chen <bingxche@amd.com>
This commit is contained in:
YC Yen-Ching Tseng
2026-08-12 03:31:03 -07:00
committed by GitHub
co-authored by yctseng0211 Chen
parent b3bffef70a
commit 00bdafe944
12 changed files with 515 additions and 432 deletions
+98 -98
View File
@@ -53,7 +53,7 @@ jobs:
id: select-workflows
run: |
if [[ -n "${{ inputs.job_filter }}" ]]; then
echo "workflows=pr-test-amd.yml" >> "$GITHUB_OUTPUT"
echo "workflows=pr-test-amd-rocm720.yml" >> "$GITHUB_OUTPUT"
else
echo "workflows=pr-test-amd.yml,nightly-test-amd.yml,pr-test-amd-rocm720.yml,nightly-test-amd-rocm720.yml,nightly-amd-mi355x-disagg.yml" >> "$GITHUB_OUTPUT"
fi
@@ -106,7 +106,7 @@ jobs:
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ inputs.job_filter }}" \
--workflow "pr-test-amd.yml" \
--workflow "pr-test-amd-rocm720.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
@@ -119,8 +119,8 @@ jobs:
outputs:
pr_jobs: ${{ steps.parse.outputs.pr_jobs }}
nightly_jobs: ${{ steps.parse.outputs.nightly_jobs }}
pr_rocm720_jobs: ${{ steps.parse.outputs.pr_rocm720_jobs }}
nightly_rocm720_jobs: ${{ steps.parse.outputs.nightly_rocm720_jobs }}
pr_rocm700_jobs: ${{ steps.parse.outputs.pr_rocm700_jobs }}
nightly_rocm700_jobs: ${{ steps.parse.outputs.nightly_rocm700_jobs }}
disagg_jobs: ${{ steps.parse.outputs.disagg_jobs }}
steps:
- name: Checkout code
@@ -129,37 +129,37 @@ jobs:
- name: Parse workflow files
id: parse
run: |
# Parse pr-test-amd.yml and extract job names (exclude utility jobs)
# Excluded: call-gate, check-changes, pr-test-amd-finish, cancel, check-all-jobs
pr_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd.yml | \
grep -v -E '^(call-gate|check-changes|pr-test-amd-finish|cancel|check-all-jobs)$' | \
# Parse the default ROCm 7.2 PR gate (exclude utility jobs)
# Excluded: call-gate, check-changes, finish, cancel, check-all-jobs
pr_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd-rocm720.yml | \
grep -v -E '^(call-gate|check-changes|pr-test-amd-rocm720-finish|cancel|check-all-jobs)$' | \
jq -R -s -c 'split("\n") | map(select(length > 0))')
echo "pr_jobs=$pr_jobs" >> $GITHUB_OUTPUT
echo "PR jobs: $pr_jobs"
# Parse nightly-test-amd.yml and extract job names (exclude utility jobs)
# Parse the default ROCm 7.2 nightly (exclude utility jobs)
# Excluded: check-all-jobs
nightly_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd.yml | \
nightly_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd-rocm720.yml | \
grep -v -E '^(check-all-jobs)$' | \
jq -R -s -c 'split("\n") | map(select(length > 0))')
echo "nightly_jobs=$nightly_jobs" >> $GITHUB_OUTPUT
echo "Nightly jobs: $nightly_jobs"
# Parse pr-test-amd-rocm720.yml (exclude utility jobs)
# Excluded: call-gate, check-changes, pr-test-amd-finish, cancel, check-all-jobs
pr_rocm720_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd-rocm720.yml | \
# Parse the ROCm 7.0 rollback shadow (exclude utility jobs)
# Excluded: call-gate, check-changes, finish, cancel, check-all-jobs
pr_rocm700_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/pr-test-amd.yml | \
grep -v -E '^(call-gate|check-changes|pr-test-amd-finish|cancel|check-all-jobs)$' | \
jq -R -s -c 'split("\n") | map(select(length > 0))')
echo "pr_rocm720_jobs=$pr_rocm720_jobs" >> $GITHUB_OUTPUT
echo "PR ROCm 7.2 jobs: $pr_rocm720_jobs"
echo "pr_rocm700_jobs=$pr_rocm700_jobs" >> $GITHUB_OUTPUT
echo "PR ROCm 7.0 shadow jobs: $pr_rocm700_jobs"
# Parse nightly-test-amd-rocm720.yml (exclude utility jobs)
# Parse the ROCm 7.0 rollback shadow nightly (exclude utility jobs)
# Excluded: check-all-jobs
nightly_rocm720_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd-rocm720.yml | \
nightly_rocm700_jobs=$(yq -r '.jobs | keys | .[]' .github/workflows/nightly-test-amd.yml | \
grep -v -E '^(check-all-jobs)$' | \
jq -R -s -c 'split("\n") | map(select(length > 0))')
echo "nightly_rocm720_jobs=$nightly_rocm720_jobs" >> $GITHUB_OUTPUT
echo "Nightly ROCm 7.2 jobs: $nightly_rocm720_jobs"
echo "nightly_rocm700_jobs=$nightly_rocm700_jobs" >> $GITHUB_OUTPUT
echo "Nightly ROCm 7.0 shadow jobs: $nightly_rocm700_jobs"
# Parse nightly-amd-mi355x-disagg.yml (exclude utility jobs)
# Excluded: setup, collect-results -- both run on ubuntu-latest and the
@@ -204,7 +204,7 @@ jobs:
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ matrix.job_name }}" \
--workflow "pr-test-amd.yml" \
--workflow "pr-test-amd-rocm720.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
@@ -238,84 +238,6 @@ jobs:
path: ci-data
- name: Generate Nightly Report
timeout-minutes: 15
run: |
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ matrix.job_name }}" \
--workflow "nightly-test-amd.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
# PR ROCm 7.2 CI reports using dynamic matrix
pr-rocm720-ci-reports:
name: PR ROCm720 - ${{ matrix.job_name }}
needs: [parse-workflows, fetch-actions-data]
if: ${{ !inputs.job_filter }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
job_name: ${{ fromJson(needs.parse-workflows.outputs.pr_rocm720_jobs) }}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: Install dependencies
run: pip install tabulate
- name: Download Actions data snapshot
uses: actions/download-artifact@v4
with:
name: actions-job-snapshot
path: ci-data
- name: Generate PR ROCm 7.2 Report
timeout-minutes: 15
run: |
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ matrix.job_name }}" \
--workflow "pr-test-amd-rocm720.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
# Nightly ROCm 7.2 reports using dynamic matrix
nightly-rocm720-reports:
name: Nightly ROCm720 - ${{ matrix.job_name }}
needs: [parse-workflows, fetch-actions-data]
if: ${{ !inputs.job_filter }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
job_name: ${{ fromJson(needs.parse-workflows.outputs.nightly_rocm720_jobs) }}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: Install dependencies
run: pip install tabulate
- name: Download Actions data snapshot
uses: actions/download-artifact@v4
with:
name: actions-job-snapshot
path: ci-data
- name: Generate Nightly ROCm 7.2 Report
timeout-minutes: 15
run: |
python scripts/ci/utils/query_job_status.py \
@@ -326,6 +248,84 @@ jobs:
--input-data-file ci-data/actions-job-snapshot.json \
--summary
# ROCm 7.0 rollback-shadow reports using dynamic matrix
pr-rocm700-ci-reports:
name: PR ROCm700 Shadow - ${{ matrix.job_name }}
needs: [parse-workflows, fetch-actions-data]
if: ${{ !inputs.job_filter }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
job_name: ${{ fromJson(needs.parse-workflows.outputs.pr_rocm700_jobs) }}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: Install dependencies
run: pip install tabulate
- name: Download Actions data snapshot
uses: actions/download-artifact@v4
with:
name: actions-job-snapshot
path: ci-data
- name: Generate PR ROCm 7.0 Shadow Report
timeout-minutes: 15
run: |
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ matrix.job_name }}" \
--workflow "pr-test-amd.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
# ROCm 7.0 rollback-shadow nightly reports using dynamic matrix
nightly-rocm700-reports:
name: Nightly ROCm700 Shadow - ${{ matrix.job_name }}
needs: [parse-workflows, fetch-actions-data]
if: ${{ !inputs.job_filter }}
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
job_name: ${{ fromJson(needs.parse-workflows.outputs.nightly_rocm700_jobs) }}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v5
with:
python-version: '3.10'
- name: Install dependencies
run: pip install tabulate
- name: Download Actions data snapshot
uses: actions/download-artifact@v4
with:
name: actions-job-snapshot
path: ci-data
- name: Generate Nightly ROCm 7.0 Shadow Report
timeout-minutes: 15
run: |
python scripts/ci/utils/query_job_status.py \
--repo ${{ github.repository }} \
--job "${{ matrix.job_name }}" \
--workflow "nightly-test-amd.yml" \
--hours ${{ inputs.hours || '24' }} \
--input-data-file ci-data/actions-job-snapshot.json \
--summary
# MI355X 2N 1P1D disagg nightly reports using dynamic matrix
nightly-disagg-reports:
name: Nightly MI355X Disagg - ${{ matrix.job_name }}