# ==========================================
# ACTUAL TEST CASES
# ==========================================

test_cases:
  - name: "Qwen3-32B-W8A8-a3-feature-stack3"
    model: "vllm-ascend/Qwen3-32B-W8A8"
    envs:
      VLLM_USE: "1"
      TASK_QUEUE_ENABLE: "1"
      HCCL_OP_EXPANSION_MODE: "AIV"
      OMP_PROC_BIND: "false"
      VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE: "1"
      VLLM_ASCEND_ENABLE_FLASHCOMM: "1"
      SERVER_PORT: "DEFAULT_PORT"
    prompts:
      - "9.11 and 9.8, which is greater?"
    api_keyword_args:
      chat_template_kwargs:
        enable_thinking: true
    server_cmd:
      - "--quantization"
      - "ascend"
      - "--tensor-parallel-size"
      - "4"
      - "--port"
      - "$SERVER_PORT"
      - "--trust-remote-code"
      - "--reasoning-parser"
      - "qwen3"
      - "--distributed_executor_backend"
      - "mp"
      - "--gpu-memory-utilization"
      - "0.9"
      - "--block-size"
      - "128"
      - "--max-num-seqs"
      - "256"
      - "--enforce-eager"
      - "--max-model-len"
      - "35840"
      - "--max-num-batched-tokens"
      - "35840"
      - "--additional-config"
      - '{"enable_weight_nz_layout":true, "weight_prefetch_config":{"enabled": true}}'
      - "--compilation-config"
      - '{"cudagraph_mode":"FULL_DECODE_ONLY", "cudagraph_capture_sizes":[1,8,24,48,60]}'
    test_content:
      - "chat_completion"
    benchmarks:
      acc:
        case_type: accuracy
        dataset_path: vllm-ascend/gsm8k-lite
        request_conf: vllm_api_general_chat
        dataset_conf: gsm8k/gsm8k_gen_0_shot_noncot_chat_prompt
        max_out_len: 10240
        batch_size: 32
        baseline: 96
        threshold: 4
      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: 240
        max_out_len: 1500
        batch_size: 60
        baseline: 1
        threshold: 0.97