v0.30.0-rc23
Breaking Changes📦 ollamaView on GitHub →
⚠ 1 breaking✨ 3 features🔧 2 symbols
Summary
This pre-release version overhauls the architecture to directly support llama.cpp, enabling GGUF compatibility and leveraging MLX for Apple Silicon acceleration. Users are encouraged to provide feedback on performance and stability.
⚠️ Breaking Changes
- The underlying architecture has changed from building on GGML to directly supporting llama.cpp, which may affect custom integrations or tooling relying on the previous internal structure.
Migration Steps
- When installing on Mac/Linux, use the command: curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.30.0-rc23 sh
- When installing on Windows, use the command: $env:OLLAMA_VERSION="0.30.0-rc23"; irm https://ollama.com/install.ps1 | iex
✨ New Features
- Direct support for llama.cpp architecture implemented.
- Compatibility with the GGUF file format is now supported.
- MLX is now used to accelerate model inference on Apple Silicon.