Ollama v0.40.17 release
The story so far
The Ollama team has released version v0.40.17, fixing issues with ChatGPT CLI recovery and graceful restarts, supporting OpenCode settings through thought metadata, and optimizing Vulkan integrated GPU LLM inference using mmap. These improvements were implemented by team members through specific commits on GitHub, including @hoyyeva, @dhiltgen, and @rpreslar4765, among others. The new version also supports MLX concurrent generation.
AI-written from the reports · Updated 6 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- Ollama releasesOllama v0.40.17 release
Ollama v0.40.17 released, fixes ChatGPT CLI recovery and graceful restart issues, and supports thinking metadata set by OpenCode. Updates Vulkan integrated graphics memory mapping, supports MLX concurrent generation, and boosts llama.cpp version to b12257.
- Ollama releasesOllama v0.40.17-rc0 released
Ollama v0.40.17-rc0 released, fixes ChatGPT CLI recovery and graceful restart issues, optimizes Vulkan integrated graphics inference performance through mmap, and supports MLX concurrent generation.
Heat over time
- Now
- 8
- Peak
- 911 Nov, 08:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.