Skip to content

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

Commits on main

llama.cpp version update (#16548)
Daniel Hiltgen committed 4 months ago
e11eeb3
jetson: add CC 87 for CUDA v13 (#16628)
Daniel Hiltgen committed 4 months ago
0a408b2
16739de
mlx: update and fix CUDA JIT packaging (#16871)
Daniel Hiltgen committed 4 months ago
570679c
llm: use host Vulkan loader on Windows (#16869)
Daniel Hiltgen committed 4 months ago
89a171c
33878e6
c191a14
docs: document max think level (#16877)
Parth Sareen committed 5 months ago
479e1cf
llm: size mmproj offload by projector memory (#16866)
Daniel Hiltgen committed 5 months ago
8365073
1148751
42c3302
f93efe2
28fbbb0
mlxrunner: unify the MTP decode paths
Jesse Gross committed 5 months ago
2e9d68d
e434a93
launch: auto-install Claude Code (#16802)
Eva H committed 5 months ago
9c02d8e
ci: pin darwin release xcode (#16788)
Parth Sareen committed 5 months ago
e1f7f9c
llama: update llama.cpp to b9672 (#16775)
Patrick Devine committed 5 months ago
8c432fc
llm: context shift allow shiftable prompts (#16764)
Jeffrey Morgan committed 5 months ago
0f047fe
9e4ed74