mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
9 lines
180 B
YAML
9 lines
180 B
YAML
enable_prefix_caching: True
|
|
max_model_len: 32768
|
|
max_num_seqs: 128
|
|
gpu_memory_utilization: 0.9
|
|
kv_cache_ratio: 0.71
|
|
tensor_parallel_size: 4
|
|
swap_space: 200
|
|
cache_queue_port: 55664
|