Ollama has released version 0.30.8, introducing several improvements and fixes. Key updates include resolving an issue with `ollama launch` selecting incorrect providers and enhancing prompt caching for better KV cache reuse. The release also brings more stable MLX inference with hardened layers and improved recurrent model support. AI
IMPACT Enhances the usability and stability of local LLM deployment tools.
RANK_REASON This is a software release for a tool that facilitates running LLMs locally, not a new frontier model release or significant industry event.
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →