Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
launch/openclaw: fix --yes flag behaviour to skip channels configuration (#15589)
1d9537b Eva H committed 7 months ago
launch: skip unchanged integration rewrite configration (#15491)
5818001 Eva H committed 7 months ago
Revert "gemma4: fix nothink case renderer (#15553)" (#15556)
5dfac38 Devon Rifkin committed 7 months ago
cgo: suppress deprecated warning to quiet down go build (#15438)
0abf3ac Daniel Hiltgen committed 7 months ago
Revert "gemma4: add nothink renderer tests (#15554)" (#15555)
ee02664 Devon Rifkin committed 7 months ago
mlx: add op wrappers for Conv2d, Pad, activations, trig, and masked SDPA (#14913)
c88fb28 Daniel Hiltgen committed 7 months ago
mlx: mixed-precision quant and capability detection improvements (#15409)
d3da29c Daniel Hiltgen committed 7 months ago
gemma4: be less strict about whitespace before bare keys (#15494)
9330bb9 Devon Rifkin committed 7 months ago
gemma4: update renderer to match new jinja template (#15490)
40a1317 Devon Rifkin committed 7 months ago
model/parsers: fix missing parallel tool call indices (#15467)
fdfe9ce Devon Rifkin committed 7 months ago
app/ui: re-validate image attachments when selected model changes (#15272)
9517864 Matteo Celani committed 7 months ago
modelfiles: fix /save command and add shortname for safetensors based models (#15413)
eb97274 Patrick Devine committed 7 months ago
fix: improve error message for unknown input item type in responses API (#15424)
612f0a1 7. Sun committed 7 months ago
app: restore launch default and refine launch sidebar open for app (#15437)
673726f Parth Sareen committed 7 months ago