[Fix] Try to fix nvcc compilation error (#21246)

.github/workflows/nightly-test-nvidia.yml

@@ -27,6 +27,7 @@ on:
           - 'nightly-test-perf-8-gpu-b200'
           - 'nightly-test-kernel-1-gpu-h100'
           - 'nightly-test-diffusion-comparison'
+          - 'nightly-test-kernel-8-gpu-h200'
   workflow_call:
     inputs:
       ref:
@@ -114,6 +115,38 @@ jobs:
       - uses: ./.github/actions/upload-cuda-coredumps
         if: always()
 
+  nightly-test-kernel-8-gpu-h200:
+    if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-8-gpu-h200')
+    runs-on: 8-gpu-h200
+    timeout-minutes: 240
+    env:
+      SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1"
+      SGLANG_JIT_DEEPGEMM_FAST_WARMUP: true
+      SGLANG_PR_TEST_BYPASS_MAINTENANCE_ON_MAIN: ${{ github.ref == 'refs/heads/main' && 'true' || 'false' }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - uses: ./.github/actions/check-maintenance
+        with:
+          github-token: ${{ github.token }}
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh
+
+      - name: Run multi-GPU jit kernel nightly suite
+        timeout-minutes: 90
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite nightly-kernel-8-gpu-h200 --nightly --continue-on-error
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
   # General tests - 4 GPU H100
   nightly-test-general-4-gpu-h100:
     if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-4-gpu-h100')

.github/workflows/pr-test-jit-kernel.yml

@@ -62,6 +62,33 @@ jobs:
           cd test/
           python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-1-gpu-large
 
+  jit-kernel-multigpu-unit-test:
+    if: |
+      github.event_name != 'schedule' &&
+      inputs.test_parallel_dispatch != 'true' &&
+      !inputs.target_stage
+    runs-on: 8-gpu-h200
+    timeout-minutes: 240
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-maintenance
+        with:
+          github-token: ${{ github.token }}
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run multi-GPU test
+        timeout-minutes: 45
+        run: |
+          cd test/
+          python3 run_suite.py --hw cuda --suite stage-b-kernel-unit-8-gpu-h200
+
   jit-kernel-benchmark-test:
     if: |
       github.event_name != 'schedule' &&