mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
Litellm dev 11 02 2024 (#6561)
* fix(dual_cache.py): update in-memory check for redis batch get cache Fixes latency delay for async_batch_redis_cache * fix(service_logger.py): fix race condition causing otel service logging to be overwritten if service_callbacks set * feat(user_api_key_auth.py): add parent otel component for auth allows us to isolate how much latency is added by auth checks * perf(parallel_request_limiter.py): move async_set_cache_pipeline (from max parallel request limiter) out of execution path (background task) reduces latency by 200ms * feat(user_api_key_auth.py): have user api key auth object return user tpm/rpm limits - reduces redis calls in downstream task (parallel_request_limiter) Reduces latency by 400-800ms * fix(parallel_request_limiter.py): use batch get cache to reduce user/key/team usage object calls reduces latency by 50-100ms * fix: fix linting error * fix(_service_logger.py): fix import * fix(user_api_key_auth.py): fix service logging * fix(dual_cache.py): don't pass 'self' * fix: fix python3.8 error * fix: fix init]
This commit is contained in:
parent
587d5fe277
commit
d88e8922d4
17 changed files with 303 additions and 157 deletions
|
@ -139,6 +139,7 @@ async def test_check_blocked_team():
|
|||
def test_returned_user_api_key_auth(user_role, expected_role):
|
||||
from litellm.proxy._types import LiteLLM_UserTable, LitellmUserRoles
|
||||
from litellm.proxy.auth.user_api_key_auth import _return_user_api_key_auth_obj
|
||||
from datetime import datetime
|
||||
|
||||
new_obj = _return_user_api_key_auth_obj(
|
||||
user_obj=LiteLLM_UserTable(
|
||||
|
@ -148,6 +149,7 @@ def test_returned_user_api_key_auth(user_role, expected_role):
|
|||
parent_otel_span=None,
|
||||
valid_token_dict={},
|
||||
route="/chat/completion",
|
||||
start_time=datetime.now(),
|
||||
)
|
||||
|
||||
assert new_obj.user_role == expected_role
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue