phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): handle scenario where model="azure/*" and custom_llm_provider="azure"

Browse source 
Fixes https://github.com/BerriAI/litellm/issues/4912
This commit is contained in:
Krrish Dholakia 2024-08-02 17:48:53 -07:00
parent bbf8771389
commit e6bc7e938a
5 changed files with 23 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/proxy/hooks/parallel_request_limiter.py
View file

@ -472,11 +472,10 @@ class _PROXY_MaxParallelRequestsHandler(CustomLogger):
async def async_log_failure_event(self, kwargs, response_obj, start_time, end_time):
try:
self.print_verbose(f"Inside Max Parallel Request Failure Hook")
global_max_parallel_requests = (
kwargs["litellm_params"]
.get("metadata", {})
.get("global_max_parallel_requests", None)
self.print_verbose("Inside Max Parallel Request Failure Hook")
_metadata = kwargs["litellm_params"].get("metadata", {}) or {}
global_max_parallel_requests = _metadata.get(
"global_max_parallel_requests", None
)
user_api_key = (
kwargs["litellm_params"].get("metadata", {}).get("user_api_key", None)