mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-07 09:31:35 +08:00
@@ -166,7 +166,7 @@ model_param_map = {
|
||||
],
|
||||
},
|
||||
"Qwen2-7B-Instruct": {
|
||||
"quantizations": ["None", "wint8"],
|
||||
"quantizations": ["wint4"],
|
||||
},
|
||||
"Qwen3-30B-A3B": {
|
||||
"tensor_parallel_size": 2,
|
||||
|
Reference in New Issue
Block a user