Ollama v0.40.17 adds concurrent MLX generation and Vulkan mmap support
AI summary
Ollama v0.40.17 adds concurrent generation to its MLX backend and uses mmap for Vulkan integrated GPUs, according to the release notes. The update also improves ChatGPT CLI restore and graceful restart, uses thinking metadata for OpenCode settings, and bumps llama.cpp to b12257 along with MLX and MLX-C.
In-depth insight
The release brings concrete local-model tooling improvements spanning concurrent generation, GPU memory mapping, CLI recovery, and editor settings.
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