apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686)

Browse Source 
* fix enable_thinking

* recover ernie4_5_vl_processor
This commit is contained in:
kxz2002
2025-10-30 19:45:41 +08:00
committed by GitHub
parent 0089287534
commit 7dc9d9885e
3 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/engine/request.py
View File

@@ -197,7 +197,7 @@ class Request:
guided_grammar=d.get("guided_grammar", None),
structural_tag=d.get("structural_tag", None),
guided_json_object=d.get("guided_json_object", None),
enable_thinking=d.get("enable_thinking", False),
enable_thinking=d.get("enable_thinking", None),
reasoning_max_tokens=d.get("reasoning_max_tokens", None),
trace_carrier=d.get("trace_carrier", {}),
chat_template=d.get("chat_template", None),