Litellm perf improvements 3 (#6573)

* perf: move writing key to cache, to background task

* perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils

adds 200ms on calls with pgdb connected

* fix(litellm_pre_call_utils.py'): rename call_type to actual call used

* perf(proxy_server.py): remove db logic from _get_config_from_file

was causing db calls to occur on every llm request, if team_id was set on key

* fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db

reduces latency/call by ~100ms

* fix(proxy_server.py): minor fix on existing_settings not incl alerting

* fix(exception_mapping_utils.py): map databricks exception string

* fix(auth_checks.py): fix auth check logic

* test: correctly mark flaky test

* fix(utils.py): handle auth token error for tokenizers.from_pretrained
This commit is contained in:
Krish Dholakia 2024-11-05 03:51:26 +05:30 committed by GitHub
parent 7525b6bbaa
commit 3a6ba0b955
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 137 additions and 86 deletions

View file

@ -1127,11 +1127,13 @@ async def user_api_key_auth( # noqa: PLR0915
api_key = valid_token.token
# Add hashed token to cache
await _cache_key_object(
hashed_token=api_key,
user_api_key_obj=valid_token,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
asyncio.create_task(
_cache_key_object(
hashed_token=api_key,
user_api_key_obj=valid_token,
user_api_key_cache=user_api_key_cache,
proxy_logging_obj=proxy_logging_obj,
)
)
valid_token_dict = valid_token.model_dump(exclude_none=True)