Skip to content
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

Jump to bottom

[Bug]: Regression in triton completions streaming #8362

Open
minwhoo opened this issue Feb 7, 2025 · 2 comments · May be fixed by #8386
Open

[Bug]: Regression in triton completions streaming #8362

minwhoo opened this issue Feb 7, 2025 · 2 comments · May be fixed by #8386
Assignees
@ishaan-jaff
Labels
bug Something isn't working

Comments

@minwhoo
Copy link

minwhoo commented Feb 7, 2025

What happened?

Triton completions streaming stopped working in new litellm versions.

I think the regression happened during #7337 where the some of the code for handling streaming in handler.py got lost.

Relevant log output

Traceback (most recent call last):
  File "/workspace/litellm_v1.60.6/litellm/litellm/litellm_core_utils/streaming_handler.py", line 1607, in __anext__
    chunk = next(self.completion_stream)
TypeError: 'NoneType' object is not an iterator
Traceback (most recent call last):
  File "/workspace/litellm_v1.60.6/litellm/litellm/litellm_core_utils/streaming_handler.py", line 1607, in __anext__
    chunk = next(self.completion_stream)
TypeError: 'NoneType' object is not an iterator

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

v1.60.6

Twitter / LinkedIn details

No response
@minwhoo minwhoo added the bug Something isn't working label Feb 7, 2025
@ishaan-jaff ishaan-jaff self-assigned this Feb 7, 2025
@ishaan-jaff
Copy link
Contributor

hi @minwhoo do you have a triton endpoint I can test against? Happy to make the fix asap

@minwhoo minwhoo linked a pull request Feb 8, 2025 that will close this issue
Open
@minwhoo
Copy link
Author

minwhoo commented Feb 8, 2025

I don't have any public-facing triton endpoints, but I've been testing a fix locally and submitted a pull request that seems to work for me at least.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ishaan-jaff ishaan-jaff

Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Fix triton streaming completions bug minwhoo/litellm
2 participants
@minwhoo @ishaan-jaff