specific method · not yet filed
IndexShare for multi-token prediction speculative decoding
Also called IndexShare MTP.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
core 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
the QSA top-k selection computed by the draft-extend pass over the tokens the target just accepted is held for the whole MTP iteration
coreunclearin Qwen3.8-Flash-NextSGLang