Starstruk Logo MarkStarstruk

v0.30.8

ollama/ollamav0.30.8Jun 12, 2026by github-actions[bot]

AI Summary

Enhances MLX inference stability with snapshots, improves prompt caching by decoupling it from context shifts, and fixes provider selection issues in `ollama launch`.

Key Highlights

  • Improved prompt caching with better KV cache reuse
  • MLX inference reliability improvements
  • Fixed `ollama launch` provider selection

New Features

  • Decoupled prompt caching from context shift
  • MLX snapshots during processing
  • Recurrent model support improvements

Full Release Notes

## What's Changed
* Fixed `ollama launch` selecting the wrong provider in some cases
* Improved prompt caching by decoupling it from context shift for better KV cache reuse
* More stable MLX inference with hardened linear and embedding layers
* MLX runner now creates snapshots during prompt processing and speculative decoding for improved reliability
* Improved recurrent model support with per-boundary states from the gated-delta kernels

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.7...v0.30.8