Skip to content

[Performance] optimize logging on cache hit path #14481

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 11 commits into
base: main
Choose a base branch
from
+204 −195
Draft

[Performance] optimize logging on cache hit path #14481

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
7710b44
Remove dead code
Bobronium Sep 10, 2025
51b6301
Redact once in helper fn
Bobronium Sep 10, 2025
85dc2c1
Remove dead code in _get_assembled_streaming_response
Bobronium Sep 10, 2025
591915e
Remove redundant get_standard_logging_object_payload calls
Bobronium Sep 10, 2025
cf9d065
Remove unnecessary _get_base_model_from_metadata call
Bobronium Sep 10, 2025
92a4710
Remove unnecessary statement
Bobronium Sep 10, 2025
933ab56
Add Logging.unified_success_handler
Bobronium Sep 10, 2025
5617f35
Use unified_success_handler for cache hits
Bobronium Sep 10, 2025
b781136
Add test to ensure get_standard_logging_object_payload is called exac…
Bobronium Sep 12, 2025
ca49965
Replace numerous isinstance calls with just one
Bobronium Sep 12, 2025
38c7fd5
Respect streaming in _success_handler_helper_fn
Bobronium Sep 12, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 1 addition & 5 deletions litellm/caching/caching_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,15 +534,11 @@ def _async_log_cache_hit_on_callbacks(
from litellm.litellm_core_utils.logging_worker import GLOBAL_LOGGING_WORKER

GLOBAL_LOGGING_WORKER.ensure_initialized_and_enqueue(
async_coroutine=logging_obj.async_success_handler(
async_coroutine=logging_obj.unified_success_handler(
result=cached_result, start_time=start_time, end_time=end_time, cache_hit=cache_hit
)
)

logging_obj.handle_sync_success_callbacks_for_async_calls(
result=cached_result, start_time=start_time, end_time=end_time, cache_hit=cache_hit
)

async def _retrieve_from_cache(
self, call_type: str, kwargs: Dict[str, Any], args: Tuple[Any, ...]
) -> Optional[Any]:
Expand Down
Loading
Loading