test_name: "test Kimi-K2-Instruct-W8A8 2-nodes-dp4-tp8-torchair"
model: "vllm-ascend/Kimi-K2-Instruct-W8A8"

num_nodes: 2
npu_per_node: 16
env_common:
  VLLM_USE_MODELSCOPE: true
  HCCL_BUFFSIZE: 1024
  SERVER_PORT: 8080
  OMP_PROC_BIND: false
  OMP_NUM_THREADS: 100
  NUMEXPR_MAX_THREADS: 128

deployment:
  -
    server_cmd: >
      vllm serve "vllm-ascend/Kimi-K2-Instruct-W8A8"
      --host 0.0.0.0
      --port $SERVER_PORT
      --data-parallel-size 4
      --data-parallel-size-local 2
      --data-parallel-start-rank 0
      --data-parallel-address $LOCAL_IP
      --data-parallel-rpc-port 13389
      --tensor-parallel-size 8
      --seed 1024
      --enable-expert-parallel
      --max-num-seqs 32
      --max-model-len 8192
      --max-num-batched-tokens 8192
      --quantization ascend
      --trust-remote-code
      --no-enable-prefix-caching
      --gpu-memory-utilization 0.9
      --additional-config '{"torchair_graph_config":{"enabled":true}}'

  -
    server_cmd: >
      vllm serve "vllm-ascend/Kimi-K2-Instruct-W8A8"
      --headless
      --data-parallel-size 4
      --data-parallel-size-local 2
      --data-parallel-start-rank 2
      --data-parallel-address $MASTER_IP
      --data-parallel-rpc-port 13389
      --tensor-parallel-size 8
      --seed 1024
      --enable-expert-parallel
      --max-num-seqs 32
      --max-model-len 8192
      --max-num-batched-tokens 8192
      --quantization ascend
      --trust-remote-code
      --no-enable-prefix-caching
      --gpu-memory-utilization 0.9
      --additional-config '{"torchair_graph_config":{"enabled":true}}'

benchmarks:
  perf:
    case_type: performance
    dataset_path: vllm-ascend/GSM8K-in3500-bs2800
    request_conf: vllm_api_stream_chat
    dataset_conf: gsm8k/gsm8k_gen_0_shot_cot_str_perf
    num_prompts: 512
    max_out_len: 256
    batch_size: 64
    trust_remote_code: True
    request_rate: 11.2
    baseline: 1
    threshold: 0.97
  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: 7680
    batch_size: 64
    baseline: 95
    threshold: 5