implementation detail · not yet filed
Offline weight reordering for local gate reduction
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
The up-projection weights are reordered offline so the four gate values for each output can be reduced locally inside a tile.
usedunclearin SGLangSGLang