mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
a2870ed4a9
* parser register name unify * change ernie_x1 to ernie-x1 * change ernie4_5_vl to ernie-45-vl * fix unit test
11 lines
252 B
YAML
11 lines
252 B
YAML
reasoning-parser: ernie-x1
|
|
tool_call_parser: ernie-x1
|
|
tensor_parallel_size: 4
|
|
max_model_len: 65536
|
|
max_num_seqs: 128
|
|
enable_prefix_caching: True
|
|
enable_chunked_prefill: True
|
|
gpu_memory_utilization: 0.85
|
|
graph_optimization_config:
|
|
use_cudagraph: True
|