Ollama v0.30.0-rc23: "directly support llama.cpp" & "compatibility with GGUF"
Ollama has released version 0.30.0-rc23, which directly supports llama.cpp and is compatible with the GGUF file format. This update aims to improve model inference performance, particularly on Apple Silicon. Users are encouraged to provide feedback on performance and any issues encountered during the pre-release phase.
- ▪The new version changes the architecture to directly support llama.cpp instead of GGML.
- ▪MLX is utilized to accelerate model inference on Apple Silicon.
- ▪Known issues include lack of support for laguna-xs.2 and llama3.2-vision in this pre-release.
Opening excerpt (first ~120 words) tap to expand
ollama / ollama Public Notifications You must be signed in to change notification settings Fork 16.3k Star 172k Code Issues 2.4k Pull requests 914 Actions Security and quality 0 Insights Additional navigation options Code Issues Pull requests Actions Security and quality Insights Releases v0.30.0-rc23 v0.30.0 Pre-release Pre-release Compare Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.