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

Enable model / call timeouts #2

Closed
krrishdholakia opened this issue Jul 28, 2023 · 3 comments · Fixed by #8492
Closed

Enable model / call timeouts #2

krrishdholakia opened this issue Jul 28, 2023 · 3 comments · Fixed by #8492

Comments

@krrishdholakia
Copy link
Contributor

No description provided.

@ishaan-jaff
Copy link
Contributor

what is the expected behavior here ?

@krrishdholakia
Copy link
Contributor Author

Azure hangs so:

response = completion(model=model, messages=messages, azure=azure, set_timeout=45)

where set_timeout takes in a time input in seconds.

Nice to have: It also does feel weird to pass in azure = True. The way I modified this was by setting it to be llm_provider="azure"

@krrishdholakia
Copy link
Contributor Author

implemented in v0.1.2

@danilo26 danilo26 mentioned this issue Apr 29, 2024
Closed
@Manouchehri Manouchehri mentioned this issue May 31, 2024
Merged
@krrishdholakia krrishdholakia mentioned this issue Jun 10, 2024
Closed
ishaan-jaff pushed a commit that referenced this issue Jul 24, 2024
@elabbarw
Merge pull request #2 from elabbarw/azureaillama31
b8183bf 
feat - add azure_ai llama v3.1 8B 70B and 405B to model prices json
@krrishdholakia krrishdholakia mentioned this issue Nov 22, 2024
Open
@ishaan-jaff ishaan-jaff mentioned this issue Dec 28, 2024
Merged
@shashseq shashseq mentioned this issue Feb 5, 2025
Closed
@ishaan-jaff ishaan-jaff mentioned this issue Feb 12, 2025
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

(fix #2) don't block proxy startup if license check fails & using prometheus BerriAI/litellm
2 participants
@krrishdholakia @ishaan-jaff