[Nightly][Refactor]Migrate nightly single-node model tests from .py to .yaml

.github/workflows/_e2e_nightly_single_node.yaml

@@ -28,7 +28,10 @@ on:
         type: string
         default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.1-910b-ubuntu22.04-py3.11"
       tests:
-        required: true
+        required: false
+        type: string
+      config_file_path:
+        required: false
         type: string
       name:
         required: false
@@ -44,12 +47,12 @@ defaults:
 # only cancel in-progress runs of the same workflow
 # and ignore the lint / 1 card / 4 cards test type
 concurrency:
-  group: ascend-nightly-${{ github.workflow_ref }}-${{ github.ref }}-${{ inputs.tests }}
+  group: ascend-nightly-${{ github.workflow_ref }}-${{ github.ref }}-${{ inputs.config_file_path || inputs.tests }}
   cancel-in-progress: true
 
 jobs:
   e2e-nightly:
-    name: ${{ inputs.tests }}
+    name: ${{ inputs.name || inputs.config_file_path || inputs.tests }}
     runs-on: ${{ inputs.runner }}
     timeout-minutes: 600
     container:
@@ -114,14 +117,33 @@ jobs:
           update-alternatives --install /usr/bin/clang clang /usr/bin/clang-15 20
           update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-15 20
 
-      - name: Run vllm-project/vllm-ascend test
+      - name: Validate Inputs
+        run: |
+          if [[ -z "${{ inputs.tests }}" && -z "${{ inputs.config_file_path }}" ]]; then
+            echo "Error: Either 'tests' or 'config_file_path' must be provided."
+            exit 1
+          fi
+
+      - name: Run Pytest (py-driven)
+        if: ${{ inputs.tests != '' }}
         env:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
           VLLM_CI_RUNNER: ${{ inputs.runner }}
-          BENCHMARK_HOME: /vllm-workspace/vllm-ascend/benchmark
         working-directory: /vllm-workspace/vllm-ascend
         run: |
-          # ignore test_dispatch_ffn_combine until the test is fixed
-          pytest -sv ${{ inputs.tests }} \
+          echo "Running pytest with tests path: ${{ inputs.tests }}"
+          pytest -sv "${{ inputs.tests }}" \
           --ignore=tests/e2e/nightly/single_node/ops/singlecard_ops/test_fused_moe.py
+
+      - name: Run Pytest (YAML-driven)
+        if: ${{ always() && inputs.config_file_path != '' }} 
+        env:
+          VLLM_WORKER_MULTIPROC_METHOD: spawn
+          VLLM_USE_MODELSCOPE: True
+          VLLM_CI_RUNNER: ${{ inputs.runner }}
+          CONFIG_YAML_PATH: ${{ inputs.config_file_path }}
+        working-directory: /vllm-workspace/vllm-ascend
+        run: |
+          echo "Running YAML-driven test with config: ${{ inputs.config_file_path }}"
+          pytest -sv tests/e2e/nightly/single_node/models/scripts/test_single_node.py

.github/workflows/schedule_nightly_test_a2.yaml

@@ -49,15 +49,6 @@ jobs:
       fail-fast: false
       matrix:
         test_config:
-          - name: qwen3-next
-            os: linux-aarch64-a2b3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_next.py
-          - name: qwen3-32b
-            os: linux-aarch64-a2b3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_32b.py
-          - name: qwen3-32b-in8-a2
-            os: linux-aarch64-a2b3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8.py
           - name: test_custom_op
             os: linux-aarch64-a2b3-1
             tests: tests/e2e/nightly/single_node/ops/singlecard_ops
@@ -71,10 +62,33 @@ jobs:
       name: ${{ matrix.test_config.name }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a2'
 
+  single-node-yaml-tests:
+    name: single-node
+    if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+    strategy:
+      fail-fast: false
+      matrix:
+        test_config:
+          - name: qwen3-32b
+            os: linux-aarch64-a2b3-4
+            config_file_path: Qwen3-32B.yaml
+          - name: qwen3-next-80b-a3b-instruct
+            os: linux-aarch64-a2b3-4
+            config_file_path: Qwen3-Next-80B-A3B-Instruct-A2.yaml
+          - name: qwen3-32b-int8
+            os: linux-aarch64-a2b3-4
+            config_file_path: Qwen3-32B-Int8-A2.yaml
+    uses: ./.github/workflows/_e2e_nightly_single_node.yaml
+    with:
+      runner: ${{ matrix.test_config.os }}
+      image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a2'
+      config_file_path: ${{ matrix.test_config.config_file_path }}
+      name: ${{ matrix.test_config.name }}
+
   multi-node-tests:
     name: multi-node
     if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-    needs: single-node-tests
+    needs: [single-node-tests, single-node-yaml-tests]
     strategy:
       fail-fast: false
       max-parallel: 1

.github/workflows/schedule_nightly_test_a3.yaml

@@ -109,73 +109,83 @@ jobs:
   single-node-tests:
     name: single-node
     if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
-    needs: multi-node-tests
+    needs: [multi-node-tests]
     strategy:
       fail-fast: false
       matrix:
         test_config:
-          - name: qwen3-32b-in8-a3
-            os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8.py
-          - name: qwen3-32b-int8-a3-feature-stack3
+          - name: qwen3-30b-acc
             os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_32b_int8_a3_feature_stack3.py
-          - name: qwen3-235b-a22b-w8a8-eplb
+            tests: tests/e2e/weekly/single_node/models/test_qwen3_30b_acc.py
+    uses: ./.github/workflows/_e2e_nightly_single_node.yaml
+    with:
+      runner: ${{ matrix.test_config.os }}
+      image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
+      tests: ${{ matrix.test_config.tests }}
+      name: ${{ matrix.test_config.name }}
+
+  single-node-yaml-tests:
+    name: single-node
+    if: always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+    needs: [multi-node-tests]
+    strategy:
+      fail-fast: false
+      matrix:
+        test_config:
+          # YAML-driven tests
+          - name: deepseek-r1-0528-w8a8
+            os: linux-aarch64-a3-16
+            config_file_path: DeepSeek-R1-0528-W8A8.yaml
+          - name: deepseek-r1-w8a8-hbm
             os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_235b_a22b_w8a8_eplb.py
-          - name: deepseek-r1-w8a8-eplb
+            config_file_path: DeepSeek-R1-W8A8-HBM.yaml
+          - name: deepseek-v3-2-w8a8
+            os: linux-aarch64-a3-16
+            config_file_path: DeepSeek-V3.2-W8A8.yaml
+          - name: kimi-k2-thinking
             os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_deepseek_r1_0528_w8a8_eplb.py
-          - name: deepseek-r1-w8a8-mtpx
+            config_file_path: Kimi-K2-Thinking.yaml
+          - name: mtpx-deepseek-r1-0528-w8a8
             os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_mtpx_deepseek_r1_0528_w8a8.py
+            config_file_path: MTPX-DeepSeek-R1-0528-W8A8.yaml
+          - name: qwen3-235b-a22b-w8a8
+            os: linux-aarch64-a3-16
+            config_file_path: Qwen3-235B-A22B-W8A8.yaml
+          - name: qwen3-30b-a3b-w8a8
+            os: linux-aarch64-a3-4
+            config_file_path: Qwen3-30B-A3B-W8A8.yaml
+          - name: qwen3-next-80b-a3b-instruct-w8a8
+            os: linux-aarch64-a3-4
+            config_file_path: Qwen3-Next-80B-A3B-Instruct-W8A8.yaml
+          - name: qwq-32b
+            os: linux-aarch64-a3-4
+            config_file_path: QwQ-32B.yaml
+          - name: qwen3-32b-int8
+            os: linux-aarch64-a3-4
+            config_file_path: Qwen3-32B-Int8.yaml
           - name: qwen2-5-vl-7b
             os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen2_5_vl_7b.py
+            config_file_path: Qwen2.5-VL-7B-Instruct.yaml
           - name: qwen2-5-vl-7b-epd
             os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen2_5_vl_7b_epd.py
+            config_file_path: Qwen2.5-VL-7B-Instruct-EPD.yaml
           - name: qwen2-5-vl-32b
             os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen2_5_vl_32b.py
+            config_file_path: Qwen2.5-VL-32B-Instruct.yaml
+          - name: qwen3-32b-int8-a3-feature-stack3
+            os: linux-aarch64-a3-4
+            config_file_path: Qwen3-32B-Int8-A3-Feature-Stack3.yaml
           - name: qwen3-32b-int8-prefix-cache
             os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_prefix_cache_qwen3_32b_int8.py
-          - name: deepseek-r1-0528-w8a8
-            os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_deepseek_r1_0528_w8a8.py
+            config_file_path: Prefix-Cache-Qwen3-32B-Int8.yaml
           - name: deepseek-r1-0528-w8a8-prefix-cache
             os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_prefix_cache_deepseek_r1_0528_w8a8.py
-          - name: qwq-32b-a3
-            os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwq_32b.py
-          - name: qwen3-30b-w8a8
-            os: linux-aarch64-a3-2
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_30b_w8a8.py
-          - name: qwen3-235b-w8a8
-            os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_235b_w8a8.py
-          - name: qwen3-next-w8a8
-            os: linux-aarch64-a3-4
-            tests: tests/e2e/nightly/single_node/models/test_qwen3_next_w8a8.py
-          - name: kimi-k2-thinking
-            os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_kimi_k2_thinking.py
-          - name: deepseek-r1-w8a8-hbm
-            os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_deepseek_r1_w8a8_hbm.py
-          - name: deepseek3_2-w8a8
-            os: linux-aarch64-a3-16
-            tests: tests/e2e/nightly/single_node/models/test_deepseek_v3_2_w8a8.py
-          - name: qwen3-30b-acc
-            os: linux-aarch64-a3-4
-            tests: tests/e2e/weekly/single_node/models/test_qwen3_30b_acc.py
+            config_file_path: Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
       runner: ${{ matrix.test_config.os }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
-      tests: ${{ matrix.test_config.tests }}
+      config_file_path: ${{ matrix.test_config.config_file_path }}
       name: ${{ matrix.test_config.name }}
 
   custom-ops-tests:

tests/e2e/nightly/single_node/models/configs/DeepSeek-R1-0528-W8A8.yaml

@@ -0,0 +1,94 @@
+# ==========================================
+# Shared Configurations
+# ==========================================
+
+_envs: &envs
+  OMP_NUM_THREADS: "10"
+  OMP_PROC_BIND: "false"
+  HCCL_BUFFSIZE: "1024"
+  PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
+  SERVER_PORT: "DEFAULT_PORT"
+
+_server_cmd: &server_cmd
+  - "--quantization"
+  - "ascend"
+  - "--data-parallel-size"
+  - "2"
+  - "--tensor-parallel-size"
+  - "8"
+  - "--enable-expert-parallel"
+  - "--port"
+  - "$SERVER_PORT"
+  - "--seed"
+  - "1024"
+  - "--max-model-len"
+  - "36864"
+  - "--max-num-batched-tokens"
+  - "4096"
+  - "--max-num-seqs"
+  - "16"
+  - "--trust-remote-code"
+  - "--gpu-memory-utilization"
+  - "0.9"
+  - "--speculative-config"
+  - '{"num_speculative_tokens": 1, "method": "mtp"}'
+  - "--additional-config"
+  - '{"enable_weight_nz_layout": true}'
+
+_benchmarks_acc: &benchmarks_acc
+  acc:
+    case_type: accuracy
+    dataset_path: vllm-ascend/gsm8k-lite
+    request_conf: vllm_api_general_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_chat_prompt
+    max_out_len: 32768
+    batch_size: 32
+    baseline: 95
+    threshold: 5
+
+_benchmarks_perf: &benchmarks_perf
+  perf:
+    case_type: performance
+    dataset_path: vllm-ascend/GSM8K-in3500-bs400
+    request_conf: vllm_api_stream_chat
+    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
+    num_prompts: 400
+    max_out_len: 1500
+    batch_size: 1000
+    baseline: 1
+    threshold: 0.97
+
+# ==========================================
+# ACTUAL TEST CASES
+# ==========================================
+
+test_cases:
+  - name: "DeepSeek-R1-0528-W8A8-single"
+    model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
+    envs:
+      <<: *envs
+    server_cmd: *server_cmd
+    server_cmd_extra:
+      - "--enforce-eager"
+    benchmarks:
+
+  - name: "DeepSeek-R1-0528-W8A8-aclgraph"
+    model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
+    envs:
+      <<: *envs
+    server_cmd: *server_cmd
+    benchmarks:
+      <<: *benchmarks_acc
+      <<: *benchmarks_perf
+
+  - name: "DeepSeek-R1-0528-W8A8-EPLB"
+    model: "vllm-ascend/DeepSeek-R1-0528-W8A8"
+    envs:
+      <<: *envs
+      DYNAMIC_EPLB: "true"
+    server_cmd: *server_cmd
+    server_cmd_extra:
+      - "--additional-config"
+      - '{"enable_weight_nz_layout": true, "eplb_config": {"dynamic_eplb": "true", "expert_heat_collection_interval": 1000, "algorithm_execution_interval": 50, "eplb_policy_type": 3}}'
+    benchmarks:
+      <<: *benchmarks_acc

tests/e2e/nightly/single_node/models/configs/DeepSeek-R1-W8A8-HBM.yaml

@@ -0,0 +1,42 @@
+# ==========================================
+# ACTUAL TEST CASES
+# ==========================================
+
+test_cases:
+  - name: "DeepSeek-R1-W8A8-HBM-single"
+    model: "vllm-ascend/DeepSeek-R1-W8A8"
+    envs:
+      HCCL_BUFFSIZE: "1024"
+      SERVER_PORT: "DEFAULT_PORT"
+    server_cmd:
+      - "--quantization"
+      - "ascend"
+      - "--port"
+      - "$SERVER_PORT"
+      - "--data-parallel-size"
+      - "8"
+      - "--data-parallel-size-local"
+      - "8"
+      - "--data-parallel-rpc-port"
+      - "13389"
+      - "--tensor-parallel-size"
+      - "2"
+      - "--enable-expert-parallel"
+      - "--seed"
+      - "1024"
+      - "--max-num-seqs"
+      - "32"
+      - "--max-model-len"
+      - "6000"
+      - "--max-num-batched-tokens"
+      - "6000"
+      - "--trust-remote-code"
+      - "--gpu-memory-utilization"
+      - "0.92"
+      - "--no-enable-prefix-caching"
+      - "--reasoning-parser"
+      - "deepseek_r1"
+      - "--enforce-eager"
+      - "--additional-config"
+      - '{"ascend_scheduler_config": {"enabled": false}, "torchair_graph_config": {"enabled": false, "enable_multistream_shared_expert": false}}'
+    benchmarks: