[CI] add Precision Regression Test on Nightly Run CI (#26902)

This commit is contained in:
Jared Wen
2026-06-14 12:43:57 +08:00
committed by GitHub
parent a3fd5c24be
commit 5da3b37a9d
8 changed files with 2160 additions and 1 deletions
+35
View File
@@ -27,6 +27,7 @@ on:
- 'nightly-test-kernel-1-gpu-h100'
- 'nightly-test-diffusion-comparison'
- 'nightly-test-kernel-8-gpu-h200'
- 'nightly-test-precision-8-gpu-h200'
workflow_call:
inputs:
ref:
@@ -604,6 +605,39 @@ jobs:
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
# Nightly precision regression - per-layer hidden state comparison
nightly-test-precision-8-gpu-h200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-precision-8-gpu-h200')
runs-on: 8-gpu-h200
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
- uses: ./.github/actions/check-maintenance
- name: Install dependencies
run: |
bash scripts/ci/cuda/ci_install_dependency.sh
- name: Run precision regression test
timeout-minutes: 120
env:
SGLANG_PRECISION_BASELINE_DIR: /tmp/sglang_precision_baselines
# Required: the test errors if SGLANG_PRECISION_HF_REPO is unset (no
# local-only mode). Set the var + the HF_TOKEN_PRECISION_STORE secret.
SGLANG_PRECISION_HF_REPO: ${{ vars.SGLANG_PRECISION_HF_REPO }}
SGLANG_PRECISION_HF_REVISION: ${{ vars.SGLANG_PRECISION_HF_REVISION || 'main' }}
HF_TOKEN: ${{ secrets.HF_TOKEN_PRECISION_STORE }}
SGLANG_PRECISION_COMMIT: ${{ github.sha }}
run: |
cd test
python3 run_suite.py --hw cuda --suite nightly-precision-8-gpu-h200 --nightly --continue-on-error --timeout-per-file 3600
- uses: ./.github/actions/upload-cuda-coredumps
if: failure()
# Consolidate performance metrics from all jobs
consolidate-metrics:
if: github.repository == 'sgl-project/sglang' && always()
@@ -662,6 +696,7 @@ jobs:
- nightly-test-perf-4-gpu-b200
- nightly-test-specialized-8-gpu-b200
- nightly-test-diffusion-comparison
- nightly-test-precision-8-gpu-h200
- consolidate-metrics
runs-on: ubuntu-latest
steps: