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

test_cases:
  - name: "Qwen3-32B-QuaRot"
    model: "vllm-ascend/Qwen3-32B-W8A8-QuaRot"
    envs:
      VLLM_WORKER_MULTIPROC_METHOD: "spawn"
      SERVER_PORT: "DEFAULT_PORT"
    server_cmd:
      - "--enforce-eager"
      - "--no-enable-prefix-caching"
      - "--tensor-parallel-size"
      - "2"
      - "--port"
      - "$SERVER_PORT"
      - "--max-model-len"
      - "8192"
      - "--trust-remote-code"
      - "--distributed-executor-backend"
      - "mp"
      - "--gpu-memory-utilization"
      - "0.9"
      - "--speculative-config"
      - '{"method": "eagle3", "model": "RedHatAI/Qwen3-32B-speculator.eagle3", "num_speculative_tokens": 3}'
    benchmarks:
      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: 80
        max_out_len: 1500
        batch_size: 20
        request_rate: 0
        baseline: 1
        threshold: 0.97