Deepseek V4 (#23882)

Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
Co-authored-by: yueming-yuan <yym022502@gmail.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@users.noreply.github.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Qiaolin Yu <90088090+qiaolin-yu@users.noreply.github.com>
Co-authored-by: Ethan (Yusheng) Su <11704492+yushengsu-thu@users.noreply.github.com>
Co-authored-by: Mingyi <27337995+wisclmy0611@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Yihao Wang <42559837+againstentropy@users.noreply.github.com>

.github/workflows/pr-test.yml

@@ -1419,6 +1419,110 @@ jobs:
         if: always()
         run: bash scripts/ci/cuda/ci_cleanup_venv.sh
 
+  stage-c-test-dsv4-4-gpu-b200:
+    needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'stage-c-test-dsv4-4-gpu-b200') ||
+        (
+          !inputs.target_stage &&
+          ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    runs-on: ${{ needs.check-changes.outputs.b200_runner }}
+    timeout-minutes: 240
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: needs.check-changes.outputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v6
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda*
+
+      - name: Install dependencies
+        timeout-minutes: 30
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_flash_mla.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        env:
+          CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite stage-c-test-dsv4-4-gpu-b200 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: failure()
+
+      - name: Cleanup venv
+        if: always()
+        run: bash scripts/ci/cuda/ci_cleanup_venv.sh
+
+  stage-c-test-dsv4-8-gpu-h200:
+    needs: [check-changes, call-gate, wait-for-stage-b, sgl-kernel-build-wheels]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'stage-c-test-dsv4-8-gpu-h200') ||
+        (
+          !inputs.target_stage &&
+          ((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    runs-on: 8-gpu-h200
+    timeout-minutes: 240
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.git_ref || github.sha }}
+
+      - uses: ./.github/actions/check-stage-health
+
+      - uses: ./.github/actions/check-maintenance
+
+      - name: Download artifacts
+        if: needs.check-changes.outputs.sgl_kernel == 'true'
+        uses: actions/download-artifact@v4
+        with:
+          path: sgl-kernel/dist/
+          merge-multiple: true
+          pattern: wheel-python3.10-cuda*
+
+      - name: Install dependencies
+        timeout-minutes: 30
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/cuda/ci_install_flash_mla.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        env:
+          CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
+        run: |
+          cd test
+          python3 run_suite.py --hw cuda --suite stage-c-test-dsv4-8-gpu-h200 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
+
+      - uses: ./.github/actions/upload-cuda-coredumps
+        if: failure()
+
+      - name: Cleanup venv
+        if: always()
+        run: bash scripts/ci/cuda/ci_cleanup_venv.sh
+
   # NOTE: GB200 stage temporarily disabled — no company-owned GB200 runner available yet.
   # Re-enable when a 4-gpu-gb200 runner is provisioned.
   # stage-c-test-4-gpu-gb200:
@@ -1500,6 +1604,8 @@ jobs:
         stage-c-test-deepep-4-gpu-h100,
         stage-c-test-deepep-8-gpu-h200,
         stage-c-test-4-gpu-b200,
+        stage-c-test-dsv4-4-gpu-b200,
+        stage-c-test-dsv4-8-gpu-h200,
         # stage-c-test-4-gpu-gb200,  # Temporarily disabled — no GB200 runner
       ]
     if: always()