From 8698867479c6cf41a37f161e8dc22b96baa76cdb Mon Sep 17 00:00:00 2001
From: Baizhou Zhang <sobereddiezhang@gmail.com>
Date: Fri, 12 Dec 2025 20:19:34 -0800
Subject: [PATCH] [CI]Add gb200 runner back (#15024)

---
 .github/workflows/pr-test.yml             | 74 +++++++++++------------
 test/srt/test_deepseek_v3_cutedsl_4gpu.py |  2 +-
 2 files changed, 37 insertions(+), 39 deletions(-)

diff --git a/.github/workflows/pr-test.yml b/.github/workflows/pr-test.yml
index 39e7190c8..74446bd1e 100644
--- a/.github/workflows/pr-test.yml
+++ b/.github/workflows/pr-test.yml
@@ -1228,45 +1228,44 @@ jobs:
           cd test/srt
           IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }}  --auto-partition-size 3 --timeout-per-file 1800
 
-  # TODO: Add gb200 tests back after the ci runner is fixed
-  # unit-test-backend-4-gpu-gb200:
-  #   needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
-  #   if: |
-  #     always() &&
-  #     (
-  #       (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
-  #       (
-  #         !inputs.target_stage &&
-  #         (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
-  #         ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
-  #       )
-  #     )
-  #   runs-on: 4-gpu-gb200
-  #   env:
-  #     RUNNER_LABELS: 4-gpu-gb200
-  #   strategy:
-  #     fail-fast: false
-  #   steps:
-  #     - name: Checkout code
-  #       uses: actions/checkout@v4
+  unit-test-backend-4-gpu-gb200:
+    needs: [check-changes, call-gate, unit-test-backend-2-gpu, sgl-kernel-build-wheels-arm]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'unit-test-backend-4-gpu-gb200') ||
+        (
+          !inputs.target_stage &&
+          (github.event_name == 'schedule' || (!failure() && !cancelled())) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    runs-on: 4-gpu-gb200
+    env:
+      RUNNER_LABELS: 4-gpu-gb200
+    strategy:
+      fail-fast: false
+    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-aarch64
+      - 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-aarch64
 
-  #     - name: Install dependencies
-  #       run: |
-  #         CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh
+      - name: Install dependencies
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} IS_BLACKWELL=1 GRACE_BLACKWELL=1 bash scripts/ci/ci_install_deepep.sh
 
-  #     - name: Run test
-  #       timeout-minutes: 45
-  #       run: |
-  #         cd test/srt
-  #         python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
+      - name: Run test
+        timeout-minutes: 45
+        run: |
+          cd test/srt
+          python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600
 
   pr-test-finish:
     needs:
@@ -1300,8 +1299,7 @@ jobs:
         unit-test-deepep-4-gpu,
         unit-test-deepep-8-gpu,
         unit-test-backend-4-gpu-b200,
-        # unit-test-backend-4-gpu-gb200,
-        # unit-test-backend-8-gpu-b200,  # Moved to nightly - large models only
+        unit-test-backend-4-gpu-gb200,
       ]
     if: always()
     runs-on: ubuntu-latest
diff --git a/test/srt/test_deepseek_v3_cutedsl_4gpu.py b/test/srt/test_deepseek_v3_cutedsl_4gpu.py
index b65dd45c4..f4e52d1e8 100644
--- a/test/srt/test_deepseek_v3_cutedsl_4gpu.py
+++ b/test/srt/test_deepseek_v3_cutedsl_4gpu.py
@@ -23,7 +23,7 @@ class TestDeepseekR1Nvfp4CuteDSLDeepEP(CustomTestCase):
             "--trust-remote-code",
             "--disable-radix-cache",
             "--mem-fraction-static",
-            "0.89",
+            "0.8",
             "--max-prefill-tokens",
             "16384",
             "--max-running-requests",