Skip to content

Issues: ikawrakow/ik_llama.cpp

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

12 Open 18 Closed
12 Open 18 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Split-mode row
#254 opened Mar 12, 2025 by davidsyoung
2
CUDA: results for MoE models are not reproducible mainline bug
#249 opened Mar 10, 2025 by ikawrakow
Feature Request: create tool to offline repack models enhancement New feature or request
#228 opened Feb 23, 2025 by ikawrakow
4 tasks done
Prevent FA usage on CUDA when K and V head sizes are different Usability
#227 opened Feb 23, 2025 by ikawrakow
Does the iqk_mul_mat.cpp support 1.58-bit quantization model?
#209 opened Feb 19, 2025 by godrosev
19
Bug: Changing system_prompt on llama-server at runtime breaks parallel processing
#199 opened Feb 9, 2025 by saood06
2
Refactor: remove usage of Q8_1 for activation quantization Refactoring
#196 opened Feb 9, 2025 by ikawrakow
Refactor: iqk_mul_mat Refactoring
#183 opened Jan 30, 2025 by ikawrakow
Feature Request: steps how to compile as cmake i struction on the origi al repo not work here. enhancement New feature or request
#159 opened Dec 22, 2024 by ajiekc905
4 tasks done
6
Refactor: update ggml library?
#133 opened Dec 11, 2024 by Nexesenex
4
Feature Request: Elliminate/reduce unnecessary copies enhancement New feature or request
#67 opened Sep 28, 2024 by ikawrakow
4 tasks done
Feature Request: Improve CPU processing speed for large contexts enhancement New feature or request
#26 opened Aug 22, 2024 by ikawrakow
4 tasks done
ProTip! Type g i on any issue or pull request to go back to the issue listing page.