xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-25 23:18:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Frontend] Improve StreamingResponse Exception Handling (#11752)

Browse Source
This commit is contained in:
Robert Shaw 2025-01-05 16:35:01 -05:00 committed by GitHub
parent eba17173d3
commit 33fc1e2e86
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/openai/serving_chat.py
View File

@ -301,7 +301,7 @@ class OpenAIServingChat(OpenAIServing):
] * num_choices
else:
tool_parsers = [None] * num_choices
except RuntimeError as e:
except Exception as e:
logger.exception("Error in tool parser creation.")
data = self.create_streaming_error_response(str(e))
yield f"data: {data}\n\n"
@ -591,7 +591,7 @@ class OpenAIServingChat(OpenAIServing):
completion_tokens=num_completion_tokens,
total_tokens=num_prompt_tokens + num_completion_tokens)
except ValueError as e:
except Exception as e:
# TODO: Use a vllm-specific Validation Error
logger.exception("Error in chat completion stream generator.")
data = self.create_streaming_error_response(str(e))

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

@ -371,7 +371,7 @@ class OpenAIServingCompletion(OpenAIServing):
# report to FastAPI middleware aggregate usage across all choices
request_metadata.final_usage_info = final_usage_info
except ValueError as e:
except Exception as e:
# TODO: Use a vllm-specific Validation Error
data = self.create_streaming_error_response(str(e))
yield f"data: {data}\n\n"