Skip to content

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

Commits on main

mlx: add compiled closure support
Jesse Gross committed 7 months ago
d3e67e3
launch: OpenCode inline config (#15586)
Eva H committed 7 months ago
698e04a
Gemma4 on MLX (#15244)
Daniel Hiltgen committed 7 months ago
2cba775
gemma4: restore e2b-style nothink prompt (#15560)
Devon Rifkin committed 7 months ago
bf2a421
launch/opencode: use inline config (#15462)
Eva H committed 7 months ago
f3cf6b7
5dfac38
mac: prevent generate on cross-compiles (#15120)
Daniel Hiltgen committed 7 months ago
a99e5d9
0abf3ac
ee02664
gemma4: add nothink renderer tests (#15554)
Devon Rifkin committed 7 months ago
1b70bb8
gemma4: fix compiler error on metal (#15550)
Daniel Hiltgen committed 7 months ago
ec29ce4
gemma4: fix nothink case renderer (#15553)
Devon Rifkin committed 7 months ago
4d75f5d
Update to ROCm 7.2.1 (#15483)
saman-amd committed 7 months ago
798fd09
40a1317
fdfe9ce
docs: add hermes agent integration guide (#15488)
Bruce MacDonald committed 7 months ago
8e6d86d
launch: update openclaw channel message (#15463)
Parth Sareen committed 7 months ago
80d3744
mlx: remove stale x86 libmlx library (#15443)
Daniel Hiltgen committed 7 months ago
6b5db12
pull/push: refine safetensors (#14946)
Daniel Hiltgen committed 7 months ago
b5918f9