mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
Sync v2.0 version of code to github repo
This commit is contained in:
@@ -0,0 +1,9 @@
|
||||
enable_mm: True
|
||||
max_model_len: 32768
|
||||
max_num_seqs: 36
|
||||
gpu_memory_utilization: 0.9
|
||||
kv_cache_ratio: 0.8
|
||||
tensor_parallel_size: 4
|
||||
quantization: wint8
|
||||
limit_mm_per_prompt: '{"image": 100, "video": 100}'
|
||||
reasoning_parser: ernie-45-vl
|
||||
Reference in New Issue
Block a user