Skip to content

[2/6] Torch GDN/KDA decode QAT with INT8 recurrent state - #2519

Draft
kaix-nv wants to merge 9 commits into
mainfrom
kaix/linear-attention-decode-first
Draft

[2/6] Torch GDN/KDA decode QAT with INT8 recurrent state#2519
kaix-nv wants to merge 9 commits into
mainfrom
kaix/linear-attention-decode-first

Remove redundant linear attention quantization scaffolding

19fd925
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Oct 4, 2026 in 0s

DCO

All commits are signed off!

View more details on DCO