ci: migrate 1-GPU model tests to test/registered/models/ (#16414)

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

@@ -184,6 +184,46 @@ jobs:
         run: |
           docker exec -w /sglang-checkout/test ci_sglang python3 run_suite.py --hw amd --suite stage-a-test-1
 
+  stage-b-test-small-1-gpu-amd:
+    needs: [check-changes, stage-a-test-1-amd]
+    if: |
+      always() &&
+      (
+        (inputs.target_stage == 'stage-b-test-small-1-gpu-amd') ||
+        (
+          !inputs.target_stage &&
+          (!failure() && !cancelled()) &&
+          ((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
+        )
+      )
+    strategy:
+      fail-fast: false
+      matrix:
+        runner: [linux-mi325-gpu-1]
+        part: [0, 1, 2, 3]
+    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_ci_start_container.sh
+        env:
+          GITHUB_WORKSPACE: ${{ github.workspace }}
+
+      - name: Install dependencies
+        run: bash scripts/ci/amd_ci_install_dependency.sh
+
+      - name: Run test
+        timeout-minutes: 30
+        run: |
+          docker exec -w /sglang-checkout/test ci_sglang python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 4
+
   multimodal-gen-test-1-gpu-amd:
     needs: [check-changes]
     if: needs.check-changes.outputs.multimodal_gen == 'true'
@@ -754,7 +794,6 @@ jobs:
         run: |
           bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
           bash scripts/ci/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
-          bash scripts/ci/amd_ci_exec.sh python3 models/test_qwen_models.py
 
   accuracy-test-2-gpu-amd:
     needs: [check-changes, accuracy-test-1-gpu-amd]
@@ -844,6 +883,7 @@ jobs:
         multimodal-gen-test-2-gpu-amd,
 
         stage-a-test-1-amd,
+        stage-b-test-small-1-gpu-amd,
         unit-test-backend-1-gpu-amd,
         unit-test-backend-2-gpu-amd,
         unit-test-backend-8-gpu-amd,

.github/workflows/pr-test.yml

@@ -532,7 +532,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        partition: [0, 1, 2, 3, 4]
+        partition: [0, 1, 2, 3, 4, 5, 6, 7]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -559,7 +559,7 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
             CONTINUE_ON_ERROR_FLAG="--continue-on-error"
           fi
-          python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 5 $CONTINUE_ON_ERROR_FLAG
+          python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 8 $CONTINUE_ON_ERROR_FLAG
 
   stage-b-test-large-1-gpu:
     needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
@@ -891,7 +891,7 @@ jobs:
       fail-fast: false
       max-parallel: ${{ fromJson(needs.check-changes.outputs.max_parallel) }}
       matrix:
-        part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
+        part: [0, 1, 2, 3, 4, 5]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -922,7 +922,7 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
             CONTINUE_ON_ERROR_FLAG="--continue-on-error"
           fi
-          python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
+          python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 6 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
 
   stage-b-test-4-gpu-b200: