mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
17 lines
419 B
YAML
17 lines
419 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 256
|
|
gpu_memory_utilization: 0.9
|
|
kv_cache_ratio: 0.8
|
|
tensor_parallel_size: 4
|
|
cache_queue_port: 55663
|
|
enable_chunked_prefill: True
|
|
splitwise_role: decode
|
|
engine_worker_queue_port: 6678
|
|
cache_transfer_protocol: "rdma,ipc"
|
|
rdma_comm_ports: "7671,7672,7673,7674"
|
|
pd_comm_port: "2334"
|
|
max_num_batched_tokens: 384
|
|
max_num_partial_prefills: 3
|
|
max_long_partial_prefills: 3
|
|
quantization: wint4
|