Skip to content

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

Commits on main

dflash: add the DFlash block-diffusion draft model
Jesse Gross committed 3 months ago
cf129bb
mlxrunner: add a block-diffusion drafting session
Jesse Gross committed 3 months ago
c1bf60d
0fcfc99
e7fbd52
agent/tui: stream thinking traces (#17611)
Parth Sareen committed 3 months ago
f91cb0d
8dd34b7
ci: fix race in darwin build (#17578)
Daniel Hiltgen committed 3 months ago
26936be
llama.cpp update (#17545)
Daniel Hiltgen committed 3 months ago
c82ebbd
8d8c701
4f9d09e
nn/recurrent: run the gated-delta step in one launch
Jesse Gross committed 3 months ago
ba8f2a3
721f050
accd6d6
bd3f22e
mlx: apply global scales in Dequantize
Jesse Gross committed 3 months ago
5db07ca
mlx: read scalar items at the array's element width
Jesse Gross committed 3 months ago
acf96e7
mlx update (#17476)
Daniel Hiltgen committed 3 months ago
a199313
CI: enable lint on the whole tree (#17457)
Daniel Hiltgen committed 3 months ago
b205993
lint: clean up current tree (#17456)
Daniel Hiltgen committed 3 months ago
9ea503f
3ff2dcb
imagegen: remove MLX image generation code (#16615)
Jeffrey Morgan committed 3 months ago
4713800
cmd/tui: improve prompt debug rendering (#17334)
Parth Sareen committed 3 months ago
0e2e34a
agent: accept file mentions on Enter (#17384)
Parth Sareen committed 3 months ago
76929b0
tui: avoid table detection for pipe prose (#17424)
Parth Sareen committed 3 months ago
bf7be18