From fb9582c4e15ecae392adfd4e1f4fedaf13ce835c Mon Sep 17 00:00:00 2001 From: alisonshao <54658187+alisonshao@users.noreply.github.com> Date: Tue, 4 Nov 2025 16:46:30 -0800 Subject: [PATCH] Add multi-GPU configurations to nightly-test.yml (#12585) --- .github/workflows/nightly-test.yml | 72 +++++++++++++++++++++++++++++- scripts/ci_monitor/ci_analyzer.py | 9 ++++ 2 files changed, 80 insertions(+), 1 deletion(-) diff --git a/.github/workflows/nightly-test.yml b/.github/workflows/nightly-test.yml index c95b84cc6..b2086eb4e 100644 --- a/.github/workflows/nightly-test.yml +++ b/.github/workflows/nightly-test.yml @@ -117,7 +117,77 @@ jobs: bash scripts/ci/ci_install_dependency.sh - name: Run test - timeout-minutes: 10 + timeout-minutes: 60 run: | cd test/srt python3 run_suite.py --suite nightly-1-gpu + + nightly-test-4-gpu: + if: github.repository == 'sgl-project/sglang' + runs-on: 4-gpu-h100 + steps: + - name: Checkout code + uses: actions/checkout@v4 + + - name: Install dependencies + run: | + bash scripts/ci/ci_install_dependency.sh + + - name: Run test + timeout-minutes: 30 + run: | + cd test/srt + python3 run_suite.py --suite nightly-4-gpu + + nightly-test-8-gpu-h200: + if: github.repository == 'sgl-project/sglang' + runs-on: 8-gpu-h200 + steps: + - name: Checkout code + uses: actions/checkout@v4 + + - name: Install dependencies + run: | + bash scripts/ci/ci_install_dependency.sh + + - name: Run test + timeout-minutes: 30 + run: | + cd test/srt + python3 run_suite.py --suite nightly-8-gpu-h200 + + nightly-test-8-gpu-h20: + if: github.repository == 'sgl-project/sglang' + runs-on: 8-gpu-h20 + env: + SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4" + steps: + - name: Checkout code + uses: actions/checkout@v4 + + - name: Install dependencies + run: | + bash scripts/ci/ci_install_dependency.sh + + - name: Run test + timeout-minutes: 30 + run: | + cd test/srt + python3 run_suite.py --suite nightly-8-gpu-h20 + + nightly-test-4-gpu-b200: + if: github.repository == 'sgl-project/sglang' + runs-on: 4-gpu-b200 + steps: + - name: Checkout code + uses: actions/checkout@v4 + + - name: Install dependencies + run: | + IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh + + - name: Run test + timeout-minutes: 60 + run: | + cd test/srt + python3 run_suite.py --suite nightly-4-gpu-b200 diff --git a/scripts/ci_monitor/ci_analyzer.py b/scripts/ci_monitor/ci_analyzer.py index d3c726ba4..230f3bf4f 100755 --- a/scripts/ci_monitor/ci_analyzer.py +++ b/scripts/ci_monitor/ci_analyzer.py @@ -103,6 +103,11 @@ class SGLangCIAnalyzer: "nightly": [ "nightly-test-perf-text-models", "nightly-test-eval-text-models", + "nightly-test-1-gpu", + "nightly-test-4-gpu", + "nightly-test-8-gpu-h200", + "nightly-test-8-gpu-h20", + "nightly-test-4-gpu-b200", ], "integration": [ "run-all-notebooks", @@ -190,6 +195,10 @@ class SGLangCIAnalyzer: "nightly-test-eval-vlms", "nightly-test-perf-vlms", "nightly-test-1-gpu", + "nightly-test-4-gpu", + "nightly-test-8-gpu-h200", + "nightly-test-8-gpu-h20", + "nightly-test-4-gpu-b200", ] if job_name in target_jobs: