mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
7 lines
139 B
YAML
7 lines
139 B
YAML
tensor_parallel_size: 8
|
|
max_model_len: 32768
|
|
max_num_seqs: 32
|
|
num_gpu_blocks_override: 4096
|
|
kv_cache_ratio: 0.5
|
|
reasoning_parser: ernie-x1
|