Skip to content

v0.1.8#59

Merged
rifkybujana merged 95 commits intomainfrom
dev
Apr 9, 2025
Merged

v0.1.8#59
rifkybujana merged 95 commits intomainfrom
dev

Conversation

@rifkybujana
Copy link
Copy Markdown
Collaborator

  • Better memory management in model manager
  • multi-model deployment
  • smart resource approximator for model memory allocation and kv cache allocation
  • added completions endpoint on server
  • fixed url opening through markdown
  • added status bar footer
  • added system prompt editor
  • fix UI layouting
  • added auto-scroll
  • added feature to add your own model easily

- Fix model parameter is not correctly passed to the model\
- Fix deleting a chat, crashed the application\
- Fix switching model resulting the model to generate in different chat\
- Fix does not detect AMD GPU\
- Fix EOS not detected on a finetuned model with chatml format\
- Fix force Close in chat feature\
- Fix performance issue on GPU
Merging main to continue development on branch dev
This reverts commit ba9446c.
@rifkybujana rifkybujana requested a review from Copilot April 9, 2025 11:58
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot reviewed 69 out of 70 changed files in this pull request and generated 1 comment.

Files not reviewed (1)
  • CMakeLists.txt: Language not supported
Comments suppressed due to low confidence (1)

include/config.hpp:71

  • The reduction of TEXT_SIZE from the previous value (81920) to 64*1024 may impact functionality where a larger buffer was expected. Please verify that this change meets all requirements.
constexpr size_t TEXT_SIZE = 64 * 1024;

@rifkybujana rifkybujana merged commit 1d75966 into main Apr 9, 2025
1 check failed
@rifkybujana rifkybujana deleted the dev branch April 9, 2025 12:05
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants