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(router.py): fix cooldown logic for usage-based-routing-v2 pre-call-checks

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-31 21:32:01 -07:00
parent f3c37f487a
commit e49325b234
3 changed files with 45 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/main.py
View file

@ -430,6 +430,10 @@ def mock_completion(
model=model, # type: ignore
request=httpx.Request(method="POST", url="https://api.openai.com/v1/"),
)
time_delay = kwargs.get("mock_delay", None)
if time_delay is not None:
time.sleep(time_delay)
model_response = ModelResponse(stream=stream)
if stream is True:
# don't try to access stream object,
@ -880,6 +884,7 @@ def completion(
mock_response=mock_response,
logging=logging,
acompletion=acompletion,
mock_delay=kwargs.get("mock_delay", None),
)
if custom_llm_provider == "azure":
# azure configs