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: Model Response Generation Sometimes Gets Stuck #1762

Open
3 tasks
imtuyethan opened this issue Dec 3, 2024 · 0 comments
Open
3 tasks

bug: Model Response Generation Sometimes Gets Stuck #1762

imtuyethan opened this issue Dec 3, 2024 · 0 comments
Assignees
@vansangpfiev
Labels
category: model running Inference ux, handling context/parameters, runtime type: bug Something isn't working

Comments

@imtuyethan
Copy link
Contributor

Jan version

0.5.10

Describe the Bug

https://discord.com/channels/1107178041848909847/1307915350406467664/1313071502358483025

The model occasionally gets stuck at "Generating response..." state and doesn't complete the generation. This appears to happen randomly and has been observed with different models (demonstrated with both Qwen and Llama models).

Steps to Reproduce

  1. Start a conversation with any model (observed with Qwen 2.5 7B Instruct Q4 and Llama 3.2 1B Instruct Q8)
  2. Send a prompt to the model
  3. Observe that sometimes the response gets stuck at "Generating response..." indefinitely
  4. Network tab shows pending completions requests

Screenshots / Logs

Screenshot 2024-12-03 at 9 52 25 AM Screenshot 2024-12-03 at 9 52 41 AM

What is your OS?

  • MacOS
  • Windows
  • Linux
@imtuyethan imtuyethan added the type: bug Something isn't working label Dec 3, 2024
@imtuyethan imtuyethan transferred this issue from janhq/jan Dec 3, 2024
@louis-jan louis-jan added the category: model running Inference ux, handling context/parameters, runtime label Dec 4, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@vansangpfiev vansangpfiev

Labels
category: model running Inference ux, handling context/parameters, runtime type: bug Something isn't working
Projects
Jan & Cortex
Status: Investigating
Milestone
No milestone
Development

No branches or pull requests
3 participants
@vansangpfiev @imtuyethan @louis-jan