Merge pull request BerriAI#4703 from BerriAI/litellm_only_use_interna…

…l_use_cache [Fix Memory Usage] - only use per request tracking if slack alerting is being used
nidhishs · Jul 14, 2024 · ed5114c · ed5114c
2 parents 7850814 + 69f74c1
commit ed5114c
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py
@@ -280,6 +280,10 @@ def _init_litellm_callbacks(self, llm_router: Optional[litellm.Router] = None):
  async def update_request_status(
  self, litellm_call_id: str, status: Literal["success", "fail"]
  ):
+ # only use this if slack alerting is being used
+ if self.alerting is None:
+ return
+
  await self.internal_usage_cache.async_set_cache(
  key="request_status:{}".format(litellm_call_id),
  value=status,