Keep the sparse Jensen-Shannon and Gram kernel epilogues in the input precision - #2535

Open

maxwbuckley wants to merge 3 commits into

NVIDIA:mainfrom

maxwbuckley:sm120/sparse-jensen-shannon-fp32-sqrt

Commits on Sep 3, 2026

Keep the sparse Jensen-Shannon post-processing in the input precision
maxwbuckley
committed
23ef3b6
Keep the polynomial and RBF Gram epilogues in the input precision
maxwbuckley
committed
df07908
Use the canonical NVIDIA copyright notice
maxwbuckley
committed
ba762fd