andodeki/makepad
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
makepad/libs/system_speech
History
Exact
Admin 74faf62ef1 ai: the AI hub gives way to the UI, smaller models, vision and speech 
The AI hub serves local models on the LAN and now yields GPU memory to the
UI (shrinks the chat context, then unloads; grows back after; never loads
into the UI reserve), groups models by type, and reports each model's
memory split. LLM decode on Vulkan with Splash kernels, one shared GPU
device per process, vision on chat turns, an on-device text detector,
music models and stems.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-13 12:26:21 +02:00
..
src ai: the AI hub gives way to the UI, smaller models, vision and speech 2026-10-13 12:26:21 +02:00
Cargo.toml ai: the AI hub gives way to the UI, smaller models, vision and speech 2026-10-13 12:26:21 +02:00