Skip to content

Replace onnx with ggml#22

Draft
abb128 wants to merge 4 commits intomainfrom
ggml
Draft

Replace onnx with ggml#22
abb128 wants to merge 4 commits intomainfrom
ggml

Conversation

@abb128
Copy link
Owner

@abb128 abb128 commented Jan 27, 2025 •
edited
Loading

TODO:

  • don't leak memory (ggml context, allocated tensors)
  • fix other code todos
  • convert existing models to gguf
  • script/docs to convert models to gguf
  • session flushing
  • test bindings and live captions
  • speed benchmarking and comparison
  • re-add flakes
  • investigate live captions higher cpu usage (seems related to thread count)
  • possibly support vulkan

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@abb128