[diffusion] CI: add initial nvfp4 ci test for b200 (#21767)

Co-authored-by: Mick <mickjagger19@icloud.com>

.github/workflows/pr-test-multimodal-gen.yml

@@ -9,6 +9,9 @@ on:
       sgl_kernel:
         required: true
         type: string
+      b200_runner:
+        required: true
+        type: string
       continue_on_error:
         required: false
         type: string
@@ -258,6 +261,52 @@ jobs:
       - uses: ./.github/actions/upload-cuda-coredumps
         if: always()
 
+  multimodal-gen-test-1-b200:
+    if: |
+      (inputs.target_stage == 'multimodal-gen-test-1-b200') ||
+      (
+        !inputs.target_stage &&
+        ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == 'true') || (inputs.caller_needs_failure != 'true' && !cancelled())) &&
+        inputs.multimodal_gen == 'true'
+      )
+    runs-on: ${{ inputs.b200_runner }}
+    timeout-minutes: 240
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: inputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda12.9
+
+      - name: Install dependencies
+        timeout-minutes: 20
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{inputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_dependency.sh diffusion
+
+      - name: Run diffusion server tests
+        timeout-minutes: 240
+        env:
+          RUNAI_STREAMER_MEMORY_LIMIT: 0
+          CONTINUE_ON_ERROR_FLAG: ${{ inputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd python
+          python3 sglang/multimodal_gen/test/run_suite.py \
+            --suite 1-gpu-b200 \
+            $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: always()
+
   multimodal-gen-unit-test:
     if: |
       (inputs.target_stage == 'multimodal-gen-unit-test') ||

.github/workflows/pr-test.yml

@@ -892,6 +892,7 @@ jobs:
         inputs.target_stage == 'multimodal-gen-test-2-gpu' ||
         inputs.target_stage == 'multimodal-gen-component-accuracy-1-gpu' ||
         inputs.target_stage == 'multimodal-gen-component-accuracy-2-gpu' ||
+        inputs.target_stage == 'multimodal-gen-test-1-b200' ||
         inputs.target_stage == 'multimodal-gen-unit-test' ||
         (
           !inputs.target_stage &&
@@ -903,6 +904,7 @@ jobs:
     with:
       multimodal_gen: ${{ needs.check-changes.outputs.multimodal_gen }}
       sgl_kernel: ${{ needs.check-changes.outputs.sgl_kernel }}
+      b200_runner: ${{ needs.check-changes.outputs.b200_runner }}
       continue_on_error: ${{ needs.check-changes.outputs.continue_on_error }}
       pr_head_sha: ${{ inputs.pr_head_sha || '' }}
       git_ref: ${{ inputs.git_ref || '' }}