frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-11-11 16:50:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix] enable DOTALL to match multi-line tool_call parameters in extract_tool_call_required_streaming (#24668)

Browse Source 
Signed-off-by: Shijun Yin <shijun.yin@outlook.com>
This commit is contained in:
Shijun Yin
2025-09-17 17:21:18 +08:00
committed by GitHub
parent 544fe76b95
commit 2b85697031
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/openai/serving_chat.py
View File

@ -418,7 +418,7 @@ class OpenAIServingChat(OpenAIServing):
if not function_name_returned:
# get partly generated arguments from the latest tool call
param_match = re.search(r'.*"parameters":\s*(.*)',
current_text)
current_text, re.DOTALL)
arguments = param_match.group(1) if param_match else ""
arguments, _ = OpenAIServingChat._filter_delta_text(
arguments, previous_text)