mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
6 lines
131 B
YAML
6 lines
131 B
YAML
max_model_len: 32768
|
|
max_num_seqs: 75
|
|
gpu_memory_utilization: 0.85
|
|
kv_cache_ratio: 0.75
|
|
quantization: wint4
|
|
tensor_parallel_size: 4 |