TL;DR: Ollama's latest release, v0.40.4, integrates an updated llama.cpp, enabling support for decision models and EmbeddingGemma 2.
Summary: Ollama has released version 0.40.4, which includes an update to llama.cpp (b11521). This update introduces support for decision models and EmbeddingGemma 2. Additionally, the release enhances server efficiency by reusing verified manifests and loaded models in inference routes.
Why it matters: This update expands the range of models and capabilities available to developers using Ollama for local LLM inference. Builders should explore the new decision model and EmbeddingGemma 2 support for advanced local AI applications.
Source: github_releases