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

[CI] Update job dependency and move dpsk v3.2 tests to 8-gpu suite (#12942)

Browse Source
This commit is contained in:
Baizhou Zhang
2025-11-11 23:16:47 -08:00
committed by GitHub
parent 44e391b6e9
commit 8ece99a9dc
2 changed files with 9 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.github/workflows/pr-test.yml vendored
View File

@@ -401,7 +401,7 @@ jobs:
python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 15
unit-test-backend-2-gpu:
needs: [check-changes, sgl-kernel-build-wheels]
needs: [check-changes, unit-test-backend-1-gpu, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 2-gpu-runner
@@ -472,7 +472,7 @@ jobs:
strategy:
fail-fast: false
matrix:
part: [0, 1]
part: [0, 1, 2]
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -493,7 +493,7 @@ jobs:
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3
unit-test-backend-8-gpu-h20:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
@@ -844,35 +844,6 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-h200-deepep
unit-test-backend-8-gpu-deepseek-v32:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 8-gpu-h200
env:
RUNNER_LABELS: 8-gpu-h200
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Download artifacts
if: needs.check-changes.outputs.sgl_kernel == 'true'
uses: actions/download-artifact@v4
with:
path: sgl-kernel/dist/
merge-multiple: true
pattern: wheel-python3.10-cuda12.9
- name: Install dependencies
run: |
CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-h200-deepseek-v32
unit-test-backend-4-gpu-b200:
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
if: always() && !failure() && !cancelled() &&
@@ -903,7 +874,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
unit-test-backend-4-gpu-gb200:
needs: [check-changes, sgl-kernel-build-wheels-arm]
needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
if: always() && !failure() && !cancelled() &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
runs-on: 4-gpu-gb200

11
test/srt/run_suite.py
View File

@@ -168,6 +168,8 @@ suites = {
TestFile("test_deepseek_v3_mtp.py", 275),
TestFile("test_disaggregation_hybrid_attention.py", 200),
TestFile("models/test_kimi_k2_models.py", 200),
TestFile("test_deepseek_v32_basic.py", 275),
TestFile("test_deepseek_v32_mtp.py", 275),
],
"per-commit-8-gpu-h20": [
TestFile("quant/test_w4a8_deepseek_v3.py", 520),
@@ -194,11 +196,6 @@ suites = {
"per-commit-8-gpu-h200-deepep": [
TestFile("ep/test_deepep_large.py", 338),
],
"per-commit-8-gpu-h200-deepseek-v32": [
TestFile("test_deepseek_v32_basic.py", 275),
TestFile("test_deepseek_v32_mtp.py", 275),
TestFile("test_deepseek_v32_nsabackend.py", 600),
],
"quantization_test": [
TestFile("quant/test_awq.py", 163),
TestFile("test_bnb.py", 5),
@@ -227,7 +224,9 @@ suites = {
"nightly-8-gpu-b200": [],
"nightly-4-gpu": [],
"nightly-8-gpu": [],
"nightly-8-gpu-h200": [],
"nightly-8-gpu-h200": [
TestFile("test_deepseek_v32_nsabackend.py", 600),
],
"nightly-8-gpu-h20": [],
"__not_in_ci__": [
TestFile("ascend/test_ascend_w8a8_quantization.py"),