mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
7 lines
140 B
YAML
7 lines
140 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 128
|
|
kv_cache_ratio: 0.75
|
|
tensor_parallel_size: 1
|
|
quantization: wint4
|
|
enable_static_graph_inference: True
|