max_model_len: 32768
max_num_seqs: 16
gpu_memory_utilization: 0.9
kv_cache_ratio: 0.9
tensor_parallel_size: 4
splitwise_role: prefill
enable_prefix_caching: True
cache_queue_port: 55664
engine_worker_queue_port: 6677
cache_transfer_protocol: "rdma,ipc"
rdma_comm_ports: "7675,7676,7677,7678"
pd_comm_port: "2333"
quantization: wint4