[ci]use H20 to run disaggregation test (#11543)

.github/workflows/pr-test-h20.yml

@@ -1,106 +0,0 @@
-name: PR Test (H20)
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-    types: [synchronize, labeled]
-  workflow_dispatch:
-    inputs:
-      version:
-        required: true
-        type: choice
-        default: 'release'
-        options:
-          - 'release'
-          - 'nightly'
-
-concurrency:
-  group: pr-test-h20-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  check-changes:
-    runs-on: ubuntu-latest
-    outputs:
-      h20_files: ${{ steps.filter.outputs.h20_files }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Fail if the PR does not have the 'run-ci' label
-        if: github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'run-ci')
-        run: |
-          echo "This pull request does not have the 'run-ci' label. Failing the workflow."
-          exit 1
-
-      - name: Fail if the PR is a draft
-        if: github.event_name == 'pull_request' && github.event.pull_request.draft == true
-        run: |
-          echo "This pull request is a draft. Failing the workflow."
-          exit 1
-
-      - name: Detect file changes
-        id: filter
-        uses: dorny/paths-filter@v3
-        with:
-          filters: |
-            h20_files:
-              - "python/sglang/srt/models/deepseek*"
-              - "python/sglang/srt/layers/moe/**"
-              - ".github/workflows/pr-test-h20.yml"
-              - "python/pyproject.toml"
-
-  per-commit-8-gpu-h20:
-    needs: [check-changes]
-    if: needs.check-changes.outputs.h20_files == 'true'
-    runs-on: 8-gpu-h20
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Install dependencies
-        run: |
-          bash scripts/ci/ci_install_dependency.sh
-
-      - name: Run test
-        timeout-minutes: 20
-
-        run: |
-          cd test/srt
-          python3 run_suite.py --suite per-commit-8-gpu-h20
-
-  pr-test-h20-finish:
-    needs: [
-      check-changes,
-      per-commit-8-gpu-h20,
-    ]
-    if: always()
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check all dependent job statuses
-        run: |
-          # Convert the 'needs' context to a JSON string
-          json_needs='${{ toJson(needs) }}'
-
-          # Get a list of all job names from the JSON keys
-          job_names=$(echo "$json_needs" | jq -r 'keys_unsorted[]')
-
-          for job in $job_names; do
-            # For each job, extract its result
-            result=$(echo "$json_needs" | jq -r --arg j "$job" '.[$j].result')
-
-            # Print the job name and its result
-            echo "$job: $result"
-
-            # Check for failure or cancellation and exit if found
-            if [[ "$result" == "failure" || "$result" == "cancelled" ]]; then
-              echo "The above jobs failed."
-              exit 1
-            fi
-          done
-
-          # If the loop completes, all jobs were successful
-          echo "All jobs completed successfully"
-          exit 0

.github/workflows/pr-test.yml

@@ -350,6 +350,39 @@ jobs:
           cd test/srt
           python3 run_suite.py --suite per-commit-8-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
 
+  unit-test-backend-8-gpu-h20:
+    needs: [check-changes, unit-test-backend-2-gpu, sgl-kernel-build-wheels]
+    if: always() && !failure() && !cancelled() &&
+        ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+    runs-on: 8-gpu-h20
+    env:
+      SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
+    strategy:
+      fail-fast: false
+      matrix:
+        part: [0, 1]
+    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
+
+      - name: Install dependencies
+        run: |
+          CUSTOM_BUILD_SGL_KERNEL=${{needs.check-changes.outputs.sgl_kernel}} bash scripts/ci/ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 20
+        run: |
+          cd test/srt
+          python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2
+
   performance-test-1-gpu-part-1:
     needs: [check-changes, sgl-kernel-build-wheels]
     if: always() && !failure() && !cancelled() &&