FOSSWire
ai-local-edge

Ollama v0.40.4-rc1 adds Kev decision scoring for MLX

Brief written by the FOSSWire AI editor from Ollama Local AI Runtimes

1 min read Impact: 4/10

Key Takeaway

Ollama's new release candidate introduces Kev decision scoring support for the MLX framework.

Summary

The v0.40.4-rc1 release candidate for Ollama introduces Kev decision scoring capabilities specifically for MLX. This update allows for loading Kev models with FP32 decision heads and release metadata. Additionally, it implements System One scoring support featuring shared-state caching and specific limits for Kev.

Technical changes in v0.40.4-rc1

  • Support for loading Kev models including their FP32 decision head and release metadata.
  • Implementation of System One scoring.
  • Integration of shared-state caching for scoring.
  • Introduction of Kev-specific limits.

Original reference: github.com →