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

test_cases:
  - name: "Qwen3-30B-A3B-W4A8-llm-compressor"
    model: "vllm-ascend/Qwen3-30B-A3B-Instruct-2507-quantized.w4a8"
    envs:
      OMP_PROC_BIND: "false"
      OMP_NUM_THREADS: "1"
      HCCL_BUFFSIZE: "1024"
      HCCL_OP_EXPANSION_MODE: "AIV"
      PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
      SERVER_PORT: "DEFAULT_PORT"
    server_cmd:
      - "--no-enable-prefix-caching"
      - "--tensor-parallel-size"
      - "2"
      - "--port"
      - "$SERVER_PORT"
      - "--max-model-len"
      - "40960"
      - "--max-num-batched-tokens"
      - "16384"
      - "--max-num-seqs"
      - "128"
      - "--trust-remote-code"
      - "--gpu-memory-utilization"
      - "0.8"
      - "--compilation-config"
      - '{"cudagraph_mode": "FULL_DECODE_ONLY"}'
    benchmarks:
      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: 10