phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(proxy_server.py): expose flag to disable retries when max parallel request limit is hit

Browse source
This commit is contained in:
Krrish Dholakia 2024-08-22 16:49:52 -07:00
parent 73a5921262
commit b0706a6f8f
2 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

7
litellm/proxy/proxy_server.py
View file

@ -2672,6 +2672,13 @@ def giveup(e):
and isinstance(e.message, str)
and "Max parallel request limit reached" in e.message
)
if (
general_settings.get("disable_retry_on_max_parallel_request_limit_error")
is True
):
return True # giveup if queuing max parallel request limits is disabled
if result:
verbose_proxy_logger.info(json.dumps({"event": "giveup", "exception": str(e)}))
return result