Ollama v0.40.17 Released
Key point
Ollama v0.40.17 has been released. It includes improvements to ChatGPT CLI restore and graceful restart, mmap usage for Vulkan integrated GPUs, and support for concurrent generation in MLX.
Ollama v0.40.17 has been released. This update includes improvements to ChatGPT CLI restore and graceful restart, and the use of thinking metadata for OpenCode settings in cmd/launch.
Additionally, mmap is now used for Vulkan integrated GPUs, and support for concurrent generation has been added for MLX. The version of llama.cpp has been bumped to b12257, and versions for MLX and MLX-C have also been updated.
This item is a summary. The full, checkable version is at the original source:
Read the original at Ollama ↗