chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] Fix CI - unit-test-backend-1-gpu-amd-mi35x and unit-test-backend-2-gpu-amd, stage-b-test-small-1-gpu-amd (#16675)

Browse Source 
Co-authored-by: Bingxu Chen <bingxche@amd.com>
This commit is contained in:
YC Tseng
2026-01-08 10:16:27 -08:00
committed by GitHub
co-authored by Bingxu Chen
parent fbc24886dd
commit 4e999404c3
60 changed files with 106 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd.yml
+44 -85
View File
@@ -224,7 +224,46 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 12
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 12
stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-small-1-gpu-amd-mi35x') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- 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: 30
run: |
bash scripts/ci/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x
stage-b-test-large-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
@@ -545,87 +584,8 @@ jobs:
run: |
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
unit-test-backend-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-1-gpu-amd-mi35x') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- 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: 15
run: |
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd-mi35x
unit-test-backend-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'unit-test-backend-2-gpu-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
part: [0, 1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- 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: 30
run: |
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
unit-test-backend-8-gpu-amd:
needs: [check-changes, unit-test-backend-2-gpu-amd]
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
@@ -673,7 +633,7 @@ jobs:
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
unit-test-backend-8-gpu-amd-mi35x:
needs: [check-changes, unit-test-backend-2-gpu-amd]
needs: [check-changes, stage-a-test-1-amd]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
strategy:
@@ -806,7 +766,7 @@ jobs:
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
performance-test-2-gpu-amd:
needs: [check-changes, unit-test-backend-2-gpu-amd]
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
@@ -965,10 +925,9 @@ jobs:
stage-a-test-1-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-2-gpu-amd,
unit-test-backend-1-gpu-amd,
unit-test-backend-1-gpu-amd-mi35x,
unit-test-backend-2-gpu-amd,
unit-test-backend-8-gpu-amd,
unit-test-backend-8-gpu-amd-mi35x,
performance-test-1-gpu-part-1-amd,