mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
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:
parent
7525b6bbaa
commit
3a6ba0b955
14 changed files with 137 additions and 86 deletions
|
@ -281,21 +281,6 @@ class OpenTelemetry(CustomLogger):
|
|||
# End Parent OTEL Sspan
|
||||
parent_otel_span.end(end_time=self._to_ns(datetime.now()))
|
||||
|
||||
async def async_post_call_success_hook(
|
||||
self,
|
||||
data: dict,
|
||||
user_api_key_dict: UserAPIKeyAuth,
|
||||
response: Union[Any, ModelResponse, EmbeddingResponse, ImageResponse],
|
||||
):
|
||||
from opentelemetry import trace
|
||||
from opentelemetry.trace import Status, StatusCode
|
||||
|
||||
parent_otel_span = user_api_key_dict.parent_otel_span
|
||||
if parent_otel_span is not None:
|
||||
parent_otel_span.set_status(Status(StatusCode.OK))
|
||||
# End Parent OTEL Sspan
|
||||
parent_otel_span.end(end_time=self._to_ns(datetime.now()))
|
||||
|
||||
def _handle_sucess(self, kwargs, response_obj, start_time, end_time):
|
||||
from opentelemetry import trace
|
||||
from opentelemetry.trace import Status, StatusCode
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue