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

add OOM handler for MIG profiles

Browse Source
This commit is contained in:
Meshcheryakov Ilya 2024-05-30 00:58:17 +03:00
parent 6859920848
commit a0bfdf2c92
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
clearml_serving/serving/main.py
View File

@ -123,7 +123,7 @@ async def serve_model(model_id: str, version: Optional[str] = None, request: Uni
except ValueError as ex:
session_logger.report_text("[{}] Exception [{}] {} while processing request: {}\n{}".format(
instance_id, type(ex), ex, request, "".join(traceback.format_exc())))
if "CUDA out of memory. " in str(ex):
if "CUDA out of memory. " in str(ex) or "NVML_SUCCESS == r INTERNAL ASSERT FAILED" in str(ex):
raise CUDAException(exception=ex)
else:
raise HTTPException(status_code=422, detail="Error [{}] processing request: {}".format(type(ex), ex))