[AMD] Add 4-GPU test suite for MI325 runners (#20294)

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

@@ -42,6 +42,7 @@ on:
           - stage-b-test-2-gpu-large-amd
           - multimodal-gen-test-1-gpu-amd
           - multimodal-gen-test-2-gpu-amd
+          - stage-c-test-4-gpu-amd
           - stage-c-test-large-8-gpu-amd
           - stage-c-test-large-8-gpu-amd-mi35x
           - stage-b-test-large-8-gpu-disaggregation-amd
@@ -778,6 +779,62 @@ jobs:
           free -h
 
 
+  stage-c-test-4-gpu-amd:
+    needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
+    if: |
+      always() &&
+      (
+        (contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-4-gpu-amd,')) ||
+        (
+          !(inputs.target_stage || inputs.target_stage_select) &&
+          (!failure() && !cancelled()) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    strategy:
+      fail-fast: false
+      matrix:
+        runner: [linux-mi325-4gpu-sglang]
+        part: [0, 1]
+    runs-on: ${{matrix.runner}}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
+
+      - name: Ensure VRAM is clear
+        run: bash scripts/ensure_vram_clear.sh rocm
+
+      - name: Start CI container
+        run: bash scripts/ci/amd/amd_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: bash scripts/ci/amd/amd_ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 60
+        run: |
+          bash scripts/ci/amd/amd_ci_exec.sh \
+            -e NCCL_CUMEM_ENABLE=0 \
+            -e NCCL_NVLS_ENABLE=0 \
+            -e RCCL_MSCCL_ENABLE=0 \
+            -e SGLANG_USE_ROCM700A=1 \
+            -w "/sglang-checkout/test" \
+            python3 run_suite.py \
+              --hw amd \
+              --suite stage-c-test-4-gpu-amd \
+              --auto-partition-id ${{ matrix.part }} \
+              --auto-partition-size 2 \
+              --timeout-per-file 1800 \
+              --enable-retry \
+              --max-attempts 2 \
+              --retry-wait-seconds 120 \
+              --retry-timeout-increase 0 \
+              ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
+
   stage-c-test-large-8-gpu-amd:
     needs: [check-changes, call-gate, stage-b-test-1-gpu-small-amd, stage-b-test-2-gpu-large-amd]
     if: |
@@ -997,6 +1054,7 @@ jobs:
         stage-b-test-1-gpu-large-amd,
         stage-b-test-2-gpu-large-amd,
         stage-b-test-large-8-gpu-35x-disaggregation-amd,
+        stage-c-test-4-gpu-amd,
         stage-c-test-large-8-gpu-amd,
         stage-c-test-large-8-gpu-amd-mi35x,
       ]