Skip to content

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

Commits on main

launch: add openclaw channels setup (#15407)
Parth Sareen committed 7 months ago
4e16f56
55308f1
f86a969
dde0912
mlx: use default http client (#15405)
Patrick Devine committed 7 months ago
780556c
gemma4: add missing file (#15394)
Daniel Hiltgen committed 7 months ago
dfae363
gemma4: enable flash attention (#15378)
Daniel Hiltgen committed 7 months ago
e823bff
mlx: Improve M5 performance with NAX (#15345)
Daniel Hiltgen committed 7 months ago
8968740
model/parsers: add gemma4 tool call repair (#15374)
Devon Rifkin committed 7 months ago
8c8f8f3
app: update featured models (#15373)
Bruce MacDonald committed 7 months ago
26a58b2
34a790a
4589fa2
4bc2728
49d5fd5
3cd2b03
enable flash attention for gemma4 (#15296)
Daniel Hiltgen committed 7 months ago
c8e0878
bb0c58e
Add support for gemma4 (#15214)
Daniel Hiltgen committed 7 months ago
96b202d
tokenizer: add SentencePiece-style BPE support (#15162)
Daniel Hiltgen committed 7 months ago
cb00335