test_name: "test DeepSeek-V3.2-Exp-bf16 multi-dp"
model: "Yanguan/DeepSeek-V3.2-Exp-bf16"
num_nodes: 2
npu_per_node: 16
env_common:
  VLLM_USE_MODELSCOPE: true
  OMP_PROC_BIND: false
  OMP_NUM_THREADS: 100
  HCCL_BUFFSIZE: 1024
  SERVER_PORT: 8080
  VLLM_ASCEND_ENABLE_MLAPO: 0

deployment:
  -
    server_cmd: >
        vllm serve Yanguan/DeepSeek-V3.2-Exp-bf16 \
        --host 0.0.0.0
        --port $SERVER_PORT
        --data-parallel-address $LOCAL_IP
        --data-parallel-size 2
        --data-parallel-size-local 1
        --data-parallel-rpc-port 13389 
        --tensor-parallel-size 16 
        --seed 1024 
        --enable-expert-parallel 
        --max-num-seqs 16 
        --max-model-len 17450 
        --max-num-batched-tokens 17450 
        --trust-remote-code 
        --no-enable-prefix-caching 
        --gpu-memory-utilization 0.9 
        --additional-config '{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'

  -
    server_cmd: >
        vllm serve Yanguan/DeepSeek-V3.2-Exp-bf16 \
        --headless
        --data-parallel-size 2 
        --data-parallel-size-local 1 
        --data-parallel-start-rank 1 
        --data-parallel-address $MASTER_IP
        --data-parallel-rpc-port 13389 
        --tensor-parallel-size 16 
        --seed 1024 
        --max-num-seqs 16 
        --max-model-len 17450 
        --max-num-batched-tokens 17450 
        --enable-expert-parallel 
        --trust-remote-code 
        --no-enable-prefix-caching 
        --gpu-memory-utilization 0.92 
        --additional-config '{"ascend_scheduler_config":{"enabled":true},"torchair_graph_config":{"enabled":true,"graph_batch_sizes":[16]}}'
benchmarks: