ClearML/clearml-serving
1
0
Fork 0
mirror of https://github.com/clearml/clearml-serving synced 2025-06-26 18:16:00 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

force exit using os._exit

Browse Source
This commit is contained in:
Eugen Ajechiloae 2024-08-15 15:55:34 +03:00
parent 1f4e1599e3
commit 4fa5b5aa36
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
clearml_serving/serving/main.py
View File

@ -1,7 +1,6 @@
import os import os
import traceback import traceback
import gzip import gzip
import sys
from fastapi import FastAPI, Request, Response, APIRouter, HTTPException from fastapi import FastAPI, Request, Response, APIRouter, HTTPException
from fastapi.routing import APIRoute from fastapi.routing import APIRoute
@ -105,7 +104,7 @@ async def serve_model(model_id: str, version: Optional[str] = None, request: Uni
instance_id, type(ex), ex, request, "".join(traceback.format_exc()))) instance_id, type(ex), ex, request, "".join(traceback.format_exc())))
if "CUDA out of memory. " in str(ex) or "NVML_SUCCESS == r INTERNAL ASSERT FAILED" in str(ex): if "CUDA out of memory. " in str(ex) or "NVML_SUCCESS == r INTERNAL ASSERT FAILED" in str(ex):
# can't always recover from this - prefer to exit the program such that it can be restarted # can't always recover from this - prefer to exit the program such that it can be restarted
sys.exit(1) os._exit()
raise HTTPException(status_code=422, detail="Error [{}] processing request: {}".format(type(ex), ex)) raise HTTPException(status_code=422, detail="Error [{}] processing request: {}".format(type(ex), ex))
except Exception as ex: except Exception as ex:
session_logger.report_text("[{}] Exception [{}] {} while processing request: {}\n{}".format( session_logger.report_text("[{}] Exception [{}] {} while processing request: {}\n{}".format(