Refactor AMD CI. (#11128)

This commit is contained in:
Sai Enduri
2025-10-01 01:12:28 -07:00
committed by GitHub
parent 47488cc353
commit 195a59fe23
2 changed files with 15 additions and 39 deletions

View File

@@ -30,7 +30,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -56,7 +56,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-2, linux-mi325-gpu-2, linux-mi35x-gpu-2]
runner: [linux-mi325-gpu-2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -80,7 +80,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -104,7 +104,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -144,7 +144,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -178,7 +178,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-2, linux-mi325-gpu-2]
runner: [linux-mi325-gpu-2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -222,8 +222,8 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
part: [0, 1, 2, 3, 4, 5, 6, 7]
runner: [linux-mi325-gpu-1]
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -238,40 +238,16 @@ jobs:
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 50
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 8
unit-test-backend-1-gpu-amd-mi35x:
if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
strategy:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 50
run: |
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd-mi35x
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 12
unit-test-backend-2-gpu-amd:
if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-ci')
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-2, linux-mi325-gpu-2]
runner: [linux-mi325-gpu-2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -319,7 +295,7 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi300-gpu-1, linux-mi325-gpu-1]
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code