Skip to content

chore: log stack trace on error in openai server #5749

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 7, 2025
Merged

chore: log stack trace on error in openai server #5749

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f668bd0
log stack trace on error
zhengd-nv Jul 4, 2025
df5c899
Merge branch 'main' into disagg-log
zhengd-nv Jul 4, 2025
f8d6856
Merge branch 'main' into disagg-log
zhengd-nv Jul 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions tensorrt_llm/serve/openai_disagg_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import copy
import os
import signal
import traceback
from contextlib import asynccontextmanager
from http import HTTPStatus
from typing import List, Optional, Type, Union
Expand Down Expand Up @@ -168,12 +169,12 @@ async def openai_chat_completion(self, req: ChatCompletionRequest) -> Response:

async def _handle_exception(self, exception):
if isinstance(exception, CppExecutorError):
logger.error(exception)
logger.error(traceback.format_exc())
signal.raise_signal(signal.SIGINT)
elif isinstance(exception, HTTPException):
raise exception # Re-raise HTTP exceptions properly
else:
logger.error(exception)
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=f"Internal server error {str(exception)}")

async def _send_context_request(self, ctx_server: str, ctx_req: Union[CompletionRequest, ChatCompletionRequest]):
Expand Down
5 changes: 4 additions & 1 deletion tensorrt_llm/serve/openai_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -310,9 +310,11 @@ async def create_chat_response(
response = await create_chat_response(promise, postproc_params, disaggregated_params)
return JSONResponse(content=response.model_dump())
except CppExecutorError:
logger.error(traceback.format_exc())
# If internal executor error is raised, shutdown the server
signal.raise_signal(signal.SIGINT)
except Exception as e:
logger.error(traceback.format_exc())
return self.create_error_response(str(e))

async def openai_completion(self, request: CompletionRequest, raw_request: Request) -> Response:
Expand Down Expand Up @@ -436,10 +438,11 @@ async def create_completion_response(
generator, disaggregated_params)
return JSONResponse(content=response.model_dump())
except CppExecutorError:
logger.error(traceback.format_exc())
# If internal executor error is raised, shutdown the server
signal.raise_signal(signal.SIGINT)
except Exception as e:
traceback.print_exc()
logger.error(traceback.format_exc())
return self.create_error_response(str(e))

async def __call__(self, host, port):
Expand Down