Skip to content

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

Commits on main

manifest: avoid symlinks on Windows (#18852)
Daniel Hiltgen committed 1 month ago
a896fdf
Merge branch 'main' into docs_update
Anna Rahn committed 1 month ago
8d978f6
removing repetition, fixing a typo
Anna Rahn committed 1 month ago
9062a9a
changing wording
Anna Rahn committed 1 month ago
79f7e33
keeping old urls, updating model retirement page
Anna Rahn committed 1 month ago
1f51984
server: proxy cloud usage and balance APIs (#18829)
Devon Rifkin committed 1 month ago
f864601
documentation re-structuring
Anna Rahn committed 1 month ago
cba2a9c
routes: fix embed 413 vs 400 routing (#18822)
Patrick Devine committed 1 month ago
0d0720e
model: add multimodal embeddings (#18820)
Patrick Devine committed 1 month ago
efe43c5
03ed9ce
mlx: fix patch for recent mlx update (#18812)
Daniel Hiltgen committed 1 month ago
8a971df
MLX: version bump (#18720)
Daniel Hiltgen committed 1 month ago
18846f8
llama.cpp: version update (#18761)
Daniel Hiltgen committed 1 month ago
ec318f4
1970ce8
d9dec15
mlx: mitigate high latency after GPU idle (#18807)
Daniel Hiltgen committed 1 month ago
cf6c9de
test: split create integration tests out (#18470)
Daniel Hiltgen committed 1 month ago
e363843
pull: allow RCs to pull matching min_version (#18790)
Daniel Hiltgen committed 1 month ago
991421d
0fde06c
mlx: match publisher tokenizer semantics (#18779)
Daniel Hiltgen committed 1 month ago
195f4cd
mlx: Decision model improvements (#18776)
Daniel Hiltgen committed 1 month ago
27a3651
mlx: System one support (#18701)
Daniel Hiltgen committed 1 month ago
a00d083