Ollama v0.40.15 adds MiMo V2.6 support and Linux MLX CUDA loading
Ollama’s v0.40.15 release notes list support for the MiMo V2.6 model and a change to load MLX’s bundled CUDA libraries in-process on Linux. Separate v0.40.15 release-candidate reports document an llama.cpp bump to b12111 and the removal of a patch superseded by an upstream fix in rc1, followed by Kimi Code CLI support in cmd/launch in rc2. The supplied reports do not establish whether those release-candidate changes were included in the final v0.40.15 build.
The changes expand Ollama’s model compatibility and coding-agent integration while updating its Linux MLX runtime and llama.cpp dependency. The evidence does not establish whether all release-candidate changes reached the final build.
v0.40.15-rc1
- v0.40.15-rc1
-
a6d3325 - Verified This commit was created on GitHub.com and signed with GitHub’s verified signature. GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode
- Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page. No results found View all tags
v0.40.15-rc1: llama.cpp: version bump b12111 (#19530)
- v0.40.15-rc1
-
a6d3325 - Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry, something went wrong. Uh oh! There was an error while loading. Please reload this page. No results found View all tags
- Verified This commit was created on GitHub.com and signed with GitHub’s verified signature. GPG key ID: B5690EEEBB952194 Verified Learn about vigilant mode
dhiltgen tagged this 05 Nov 01:31