starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-19 11:54:17 +02:00
Code Issues Packages Projects Releases Wiki Activity
5,103 Commits 386 Branches 504 Tags
5c73c4e2eedeeb847743f43b4d2e85ff4b02be4b
Commit Graph

3 Commits

Author SHA1 Message Date
Patrick Devine
0759fface9 Revert "chore: update mlx-c bindings to 0.5.0 (#14303)" (#14316) 
This reverts commit f01a9a7859.
 2026-02-18 17:01:25 -08:00
Patrick Devine
f01a9a7859 chore: update mlx-c bindings to 0.5.0 (#14303) 2026-02-17 16:48:16 -08:00
Patrick Devine
44bdd9a2ef Add MLX runner with GLM4-MoE-Lite model support (#14185) 
This change adds a new MLX based runner which includes:

  * Method-based MLX bindings
  * Subprocess-based MLX runner (x/mlxrunner)
  * KV cache with tree management
  * A basic sampler

The GLM4-MoE-Lite model has been ported to use the new bindings.

---------

Co-authored-by: Michael Yang <git@mxy.ng>
 2026-02-10 14:57:57 -08:00