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

test_cases:
  - name: "GLM-5.1-W8A8-PrefillMC2"
    model: "Eco-Tech/GLM-5.1-w8a8"  #need update
    envs:
      OMP_PROC_BIND: "false"
      OMP_NUM_THREADS: "1"
      HCCL_OP_EXPANSION_MODE: "AIV"
      PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
      VLLM_USE_V1: "1"
      HCCL_BUFFSIZE: "1800"
      ASCEND_AGGREGATE_ENABLE: "1"
      ASCEND_TRANSPORT_PRINT: "1"
      ACL_OP_INIT_MODE: "1"
      ASCEND_A3_ENABLE: "1"
      VLLM_NIXL_ABORT_REQUEST_TIMEOUT: "300000"
      TASK_QUEUE_ENABLE: "1"
      VLLM_ASCEND_ENABLE_MLAPO: "1"
      VLLM_ASCEND_ENABLE_FLASHCOMM1: "1"
      SERVER_PORT: "DEFAULT_PORT"
    server_cmd:
      - "--tensor-parallel-size"
      - "16"
      - "--data-parallel-size"
      - "1"
      - "--port"
      - "$SERVER_PORT"
      - "--seed"
      - "1024"
      - "--max-model-len"
      - "10240"
      - "--max-num-batched-tokens"
      - "4096"
      - "--max-num-seqs"
      - "32"
      - "--trust-remote-code"
      - "--quantization"
      - "ascend"
      - "--async-scheduling"
      - "--no-enable-prefix-caching"
      - "--enable-expert-parallel"
      - "--gpu-memory-utilization"
      - "0.94"
      - "--compilation-config"
      - '{"cudagraph_mode":"FULL_DECODE_ONLY"}'
      - "--speculative-config"
      - '{"num_speculative_tokens": 3, "method":"deepseek_mtp", "enforce_eager": true}'
      - "--additional_config"
      - '{"enable_prefill_mc2": true}'      
      - "--reasoning-parser"
      - "glm45"
      - "--tool-call-parser"
      - "glm47"
      
    benchmarks:
      acc_gsm8k:
        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: 8192
        batch_size: 32
        baseline: 96.88
        temperature: 1.0
        top_p: 0.95
        thinking: true
        threshold: 5

      perf_2:
        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: 64
        max_out_len: 1500
        batch_size: 32
        request_rate: 0
        baseline: 1
        threshold: 0.97