test_name: "test Qwen3-235B-A22B disaggregated_prefill"
model: "Qwen/Qwen3-235B-A22B"
num_nodes: 2
npu_per_node: 16
env_common:
  VLLM_USE_MODELSCOPE: true
  PYTORCH_NPU_ALLOC_CONF: expandable_segments:True
  HCCL_BUFFSIZE: 1024
  HCCL_OP_EXPANSION_MODE: "AIV"
  OMP_PROC_BIND: false
  OMP_NUM_THREADS: 1
  VLLM_ASCEND_ENABLE_FLASHCOMM1: 1
  VLLM_ASCEND_ENABLE_FUSED_MC2: 2
  TASK_QUEUE_ENABLE: 1
  SERVER_PORT: 8080
  
disaggregated_prefill:
  enabled: true
  prefiller_host_index: [0]
  decoder_host_index: [1]

deployment:
  -
    server_cmd: >
        vllm serve "Qwen/Qwen3-235B-A22B"
        --host 0.0.0.0
        --port $SERVER_PORT
        --data-parallel-size 2
        --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
        --max-num-seqs 32
        --max-model-len 8192
        --max-num-batched-tokens 8192
        --enable-expert-parallel
        --trust-remote-code
        --gpu-memory-utilization 0.9
        --no-enable-prefix-caching
        --kv-transfer-config
        '{"kv_connector": "MooncakeConnectorV1",
        "kv_role": "kv_producer",
        "kv_port": "30000",
        "engine_id": "0",
        "kv_connector_extra_config": {
                  "use_ascend_direct": true,
                  "prefill": {
                          "dp_size": 2,
                          "tp_size": 8
                  },
                  "decode": {
                          "dp_size": 4,
                          "tp_size": 4
                  }
            }
        }'

  -
    server_cmd: >
        vllm serve "Qwen/Qwen3-235B-A22B"
        --host 0.0.0.0
        --port $SERVER_PORT
        --data-parallel-size 4
        --data-parallel-size-local 4
        --data-parallel-start-rank 0
        --data-parallel-address $LOCAL_IP
        --data-parallel-rpc-port 13389
        --tensor-parallel-size 4
        --seed 1024
        --max-num-seqs 32
        --max-model-len 8192
        --max-num-batched-tokens 8192
        --enable-expert-parallel
        --trust-remote-code
        --gpu-memory-utilization 0.9
        --no-enable-prefix-caching
        --compilation-config '{"cudagraph_mode":"FULL_DECODE_ONLY"}'
        --async-scheduling
        --kv-transfer-config
        '{"kv_connector": "MooncakeConnectorV1",
        "kv_role": "kv_consumer",
        "kv_port": "30100",
        "engine_id": "1",
        "kv_connector_extra_config": {
                  "use_ascend_direct": true,
                  "prefill": {
                          "dp_size": 2,
                          "tp_size": 8
                  },
                  "decode": {
                          "dp_size": 4,
                          "tp_size": 4
                  }
            }
        }'

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: 2800
    max_out_len: 1500
    batch_size: 700
    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: 512
    baseline: 97
    threshold: 3