Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

9893d39
llama.cpp update (#17186)
Daniel Hiltgen committed 4 months ago
cc62676
agent: skills system (#17203)
Parth Sareen committed 4 months ago
573386c
61e1b1b
agent: reorder working directory instruction (#17228)
Parth Sareen committed 4 months ago
5865a01
cmd: remove dead agent prompt wrappers (#17227)
Parth Sareen committed 4 months ago
e61c1c7
03d61e1
30c3903
d590830
fix launch model picker recovery (#17170)
Parth Sareen committed 4 months ago
fdcf9ef
docs: add VS Code extension setup (#17158)
Parth Sareen committed 4 months ago
76188f6
model: align gemma4 chat template handling (#17182)
Daniel Hiltgen committed 4 months ago
8a0016f
docs: collapsed previous retirements (#17167)
Michael Yang committed 4 months ago
d49b96d
3bd506b
123b1f2
5562458
mlxrunner: construct per-model state at load
Jesse Gross committed 4 months ago
c963822
mlxrunner: rename kvCache to prefixCache
Jesse Gross committed 4 months ago
dd49563
4f7786d
f1a0ffd
mlx: restore NAX in Metal v4 builds (#17160)
Daniel Hiltgen committed 4 months ago
59bd0b4
cmd: agent UI (#17017)
Parth Sareen committed 4 months ago
82f905c
cb3d98c