Skip to content

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

Commits on main

mlx: preserve generation panics during cleanup (#18886)
Daniel Hiltgen committed 1 month ago
997b98f
Add Kev decision scoring to MLX (#18976)
Daniel Hiltgen committed 1 month ago
665f9e0
a527652
Introduce clef and clef flash on cloud
Jonathan Berg committed 1 month ago
d629978
docs: update SECURITY.md
Anna Rahn committed 1 month ago
efce1a2
Revert "docs: restructuring" (#18960)
Jeffrey Morgan committed 1 month ago
8583859
726ed6c
c9e601e
typo in docs
Anna Rahn committed 1 month ago
7356968
MLX, MLX-C: version bump (#18956)
Daniel Hiltgen committed 1 month ago
374d97d
c1c5362
mlx: clip long laya states instead of rejecting them
Jeffrey Morgan committed 1 month ago
80cedab
llm: support multimodal embeddings through llama-server
Jeffrey Morgan committed 1 month ago
0c21bcf
llama: update to b11521 and use native decision support
Jeffrey Morgan committed 1 month ago
adc4aae
1ba3c76
eab97e9
db2635b
respect CLAUDE_CODE_AUTO_COMPACT_WINDOW user setting
Jonathan Berg committed 1 month ago
0c7340b
531946e
e3cddc3