biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Refactor error handling for multiple exceptions in preprocessing (#15650)

Browse Source 
Signed-off-by: JasonZhu1313 <jasonchu13@outlook.com>
This commit is contained in:
Jason (Siyu) Zhu
2025-03-27 20:27:20 -07:00
committed by GitHub
parent 4d0ec37267
commit cec8c7d7f8
4 changed files with 5 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/entrypoints/openai/serving_tokenization.py
View File

@@ -89,13 +89,7 @@ class OpenAIServingTokenization(OpenAIServing):
request.prompt,
add_special_tokens=request.add_special_tokens,
)
except ValueError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except jinja2.TemplateError as e:
except (ValueError, TypeError, jinja2.TemplateError) as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))