Ollama v0.40.17 improves CLI recovery and MLX concurrency
AI summary
Ollama v0.40.17 adds improved ChatGPT CLI restore and graceful restart, along with support for using thinking metadata in OpenCode settings. The release also introduces memory mapping for Vulkan integrated GPUs, concurrent generation in MLX, and version bumps for llama.cpp, MLX, and MLX-C. Ollama's release notes identify these changes under v0.40.17, while the listed changelog endpoint ends at v0.40.17-rc0.
In-depth insight
The update improves recovery and metadata handling in AI command-line workflows while extending local-model execution support across Vulkan integrated GPUs and MLX.
What's Changed
- Improve ChatGPT CLI restore and graceful restart by @hoyyeva in #19583
- cmd/launch: use thinking metadata for OpenCode settings by @hoyyeva in #19409
- llm: use mmap for Vulkan integrated GPUs by @dhiltgen in #19640
- rpreslar4765/Ollama by @rpreslar4765 in #17163
- mlx: support concurrent generation by @dhiltgen in #19197
- llama.cpp: version bump b12257 by @dhiltgen in #19646
- MLX, MLX-C: version bump by @dhiltgen in #19647
New Contributors
- @rpreslar4765 made their first contribution in #17163
Full Changelog: v0.40.16...v0.40.17-rc0
#Ollama#Ollama v0.40.17#ChatGPT CLI#OpenCode#MLX#MLX-C#llama.cpp