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.

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

bug: token speed is low while using Jan Windows on GPU NVIDIA 4070ti #1002

Closed
Tracked by #1063
hiento09 opened this issue Dec 14, 2023 · 1 comment
Closed
Tracked by #1063
Assignees
Labels
type: bug Something isn't working

Comments

@hiento09
Copy link
Collaborator

hiento09 commented Dec 14, 2023

Describe the bug
token speed is low while using Jan Windows on GPU NVIDIA 4070ti, just around 6/s-7/s

Screenshots
image

Desktop (please complete the following information):

  • OS: Windows 11
  • RAM 64GB
  • GPU: RTX 4070ti
  • Jan App Version: 0.4.1
  • Model: Mistral Instruct 7B Q4
@hiento09 hiento09 added the type: bug Something isn't working label Dec 14, 2023
@hiento09 hiento09 added this to Menlo Dec 14, 2023
@freelerobot freelerobot added this to the Jan on Windows milestone Dec 14, 2023
@hiento09
Copy link
Collaborator Author

hiento09 commented Dec 14, 2023

The root cause was mentioned in janhq/cortex.cpp#269

@freelerobot freelerobot moved this to Triaged (Backlog) in Menlo Dec 14, 2023
@freelerobot freelerobot moved this from Triaged (Backlog) to Todo in Menlo Dec 18, 2023
@louis-menlo louis-menlo assigned hiento09 and unassigned linhtran174 Dec 19, 2023
@hiento09 hiento09 moved this from Planned to In Progress in Menlo Dec 20, 2023
@tikikun tikikun removed their assignment Dec 21, 2023
@github-project-automation github-project-automation bot moved this from In Progress to Done in Menlo Dec 21, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type: bug Something isn't working
Projects
Archived in project
Development

No branches or pull requests

5 participants