mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
xiegegege
8 lines
150 B
YAML
8 lines
150 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 128
|
|
kv_cache_ratio: 0.75
|
|
tensor_parallel_size: 1
|
|
max_num_batched_tokens: 32768
|
|
quantization: wint8
|
|
swap_space: 100
|