CJ Pais

Ported the code from [llama.cpp PR 5896](https://github.com/ggerganov/llama.cpp/pull/5896) Should address [llama.cpp 5852](https://github.com/ggerganov/llama.cpp/issues/5852) and [llama.cpp 5863](https://github.com/ggerganov/llama.cpp/issues/5863) To fix, we set the number of tokens processed to it's correct value in ingest_images where...

This PR adds whisper.cpp support to llamafile. This addresses #17 in part. Only the server binary has been ported in this PR. Most of the work to support this was...

Qwen3 Support

7

Changes based off of [llama.cpp #12828](https://github.com/ggml-org/llama.cpp/pull/12828) Adds support for Qwen3 and Qwen3MoE models. It looks like there will be more changes when the models are released.

Release does not contain binaries for arm64 on Linux

9

Much like the title of the issue says, the release does not contain these binaries. We probably need to cross compile this, or set up a GitHub action to do...

WIP: Add tauri-specta for generating TS bindings

2

This is part of an ongoing refactor to make the whole settings deal a bit easier to deal with. Making it easier and cleaner to add new settings and reducing...

for #358 I have not tested it, I just let codex write everything @odie5533

dont crash if there's no mic

5

title

mainly for #462 needs review and testing.