Skip to content

Fix concurrency/scaling when many Python threads do streaming using *sync* completions #14816

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

Merged
merged 2 commits into from
Sep 24, 2025
Merged

Fix concurrency/scaling when many Python threads do streaming using *sync* completions #14816

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6a9ebe8
Don't submit a task to a thread if streaming logging is disabled
leventov Sep 23, 2025
0a5fe10
Make httpx's sync transport configurable
leventov Sep 23, 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
11 changes: 6 additions & 5 deletions litellm/litellm_core_utils/streaming_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1619,11 +1619,12 @@ def __next__(self): # noqa: PLR0915
completion_start_time=datetime.datetime.now()
)
## LOGGING
executor.submit(
self.run_success_logging_and_cache_storage,
response,
cache_hit,
) # log response
if not litellm.disable_streaming_logging:
executor.submit(
self.run_success_logging_and_cache_storage,
response,
cache_hit,
) # log response
choice = response.choices[0]
if isinstance(choice, StreamingChoices):
self.response_uptil_now += choice.delta.get("content", "") or ""
Expand Down
2 changes: 1 addition & 1 deletion litellm/llms/custom_httpx/http_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -915,7 +915,7 @@ def _create_sync_transport(self) -> Optional[HTTPTransport]:
if litellm.force_ipv4:
return HTTPTransport(local_address="0.0.0.0")
else:
return None
return getattr(litellm, 'sync_transport', None)


def get_async_httpx_client(
Expand Down
Loading