mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
0fad10b35a
* cuda graph support padding batch * Integrate the startup parameters for the graph optimization backend and provide support for user - defined capture sizes. * Do not insert max_num_seqs when the user specifies a capture list * Support set graph optimization config from YAML file * update cuda graph ci * fix ci bug * fix ci bug
8 lines
152 B
YAML
8 lines
152 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 128
|
|
kv_cache_ratio: 0.75
|
|
tensor_parallel_size: 1
|
|
quantization: wint4
|
|
graph_optimization_config:
|
|
graph_opt_level: 1
|