# ==========================================
# Shared Configurations
# ==========================================

_envs: &envs
  OMP_NUM_THREADS: "1"
  OMP_PROC_BIND: "false"
  TASK_QUEUE_ENABLE: "1"
  HCCL_OP_EXPANSION_MODE: "AIV"
  VLLM_ASCEND_ENABLE_FLASHCOMM1: "1"
  PYTORCH_NPU_ALLOC_CONF: "expandable_segments:True"
  VLLM_ASCEND_ENABLE_PREFETCH_MLP: "1"
  SERVER_PORT: "DEFAULT_PORT"

_server_cmd: &server_cmd
  - "--quantization"
  - "ascend"
  - "--no-enable-prefix-caching"
  - "--mm-processor-cache-gb"
  - "0"
  - "--tensor-parallel-size"
  - "2"
  - "--port"
  - "$SERVER_PORT"
  - "--max-model-len"
  - "20000"
  - "--max-num-batched-tokens"
  - "8192"
  - "--trust-remote-code"
  - "--gpu-memory-utilization"
  - "0.9"
  - "--async-scheduling"

_benchmarks: &benchmarks
  acc:
    case_type: accuracy
    dataset_path: vllm-ascend/textvqa-lite
    request_conf: vllm_api_stream_chat
    dataset_conf: textvqa/textvqa_gen_base64
    max_out_len: 2048
    batch_size: 128
    baseline: 80
    temperature: 0
    top_k: -1
    top_p: 1
    repetition_penalty: 1
    threshold: 5

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

test_cases:
  - name: "Qwen3-VL-32B-Instruct-W8A8"
    model: "Eco-Tech/Qwen3-VL-32B-Instruct-w8a8-QuaRot"
    envs:
      <<: *envs
    server_cmd: *server_cmd
    server_cmd_extra:
      - "--compilation_config"
      - '{"cudagraph_mode": "FULL_DECODE_ONLY", "cudagraph_capture_sizes": [1,12,16,20,24,32,48,64,68,72,76,80,128]}'
    benchmarks:
      <<: *benchmarks