reasoning-parser: ernie_x1
tool_call_parser: ernie_x1
tensor_parallel_size: 4
max_model_len: 65536
max_num_seqs: 128
enable_prefix_caching: True
enable_chunked_prefill: True
gpu_memory_utilization: 0.85
use_cudagraph: True
enable_custom_all_reduce: True