Skip to content

flashnext cuda: drafted rounds: first token early, n-gram table resident, deeper greedy drafts, CUDA graphs - #1786

Open
Arminova wants to merge 3 commits into
ashhart:mainfrom
Arminova:flashnext/draft-round
Open

Arminova wants to merge 3 commits into
ashhart:mainfrom
Arminova:flashnext/draft-round

flashnext cuda: drafted rounds: first token early, n-gram table resid…

bd11f9a
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
desktop-linux
succeeded Nov 1, 2026 in 9m 46s