Added:
- This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon.

Changed:
- v0.30.0

Removed:
- v0.25.0-rc0: ci: speed up release builds (#15982)
- v0.30.0-rc17
- ci and lint fixes