mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
8 lines
162 B
YAML
8 lines
162 B
YAML
num_gpu_blocks_override: 1024
|
|
max_model_len: 8192
|
|
max_num_seqs: 64
|
|
data_parallel_size: 4
|
|
tensor_parallel_size: 1
|
|
enable_expert_parallel: True
|
|
quantization: wint4
|