mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
7 lines
132 B
YAML
7 lines
132 B
YAML
max_model_len: 16384
|
|
max_num_seqs: 256
|
|
max_num_batched_tokens: 16384
|
|
tensor_parallel_size: 1
|
|
gpu_memory_utilization: 0.7
|
|
workers: 4
|