phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix(router.py): fix init line for self.default_max_parallel_requests

Browse source
This commit is contained in:
Krrish Dholakia 2024-04-20 12:08:21 -07:00
parent 4c78f8f309
commit 47e9d5f2ec
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/router.py
View file

@ -204,6 +204,7 @@ class Router:
) # use a dual cache (Redis+In-Memory) for tracking cooldowns, usage, etc.
self.default_deployment = None # use this to track the users default deployment, when they want to use model = *
self.default_max_parallel_requests = default_max_parallel_requests
if model_list:
model_list = copy.deepcopy(model_list)
@ -219,7 +220,7 @@ class Router:
) # cache to track failed call per deployment, if num failed calls within 1 minute > allowed fails, then add it to cooldown
self.num_retries = num_retries or litellm.num_retries or 0
self.timeout = timeout or litellm.request_timeout
self.default_max_parallel_requests = default_max_parallel_requests
self.retry_after = retry_after
self.routing_strategy = routing_strategy
self.fallbacks = fallbacks or litellm.fallbacks