mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
Ryan
10 lines
211 B
YAML
10 lines
211 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 128
|
|
tensor_parallel_size: 1
|
|
quantization: wint4
|
|
graph_optimization_config:
|
|
graph_opt_level: 1
|
|
sot_warmup_sizes: [2,16,32,64]
|
|
use_cudagraph: True
|
|
full_cuda_graph: False
|