Skip to content

Use Fused Kernels for Depthwise Striding Subsampler: up to 1.5x faster training - #16114

Open
MahmoudAshraf97 wants to merge 12 commits into
NVIDIA-NeMo:mainfrom
MahmoudAshraf97:fast-pre-encoder
Open

Use Fused Kernels for Depthwise Striding Subsampler: up to 1.5x faster training#16114
MahmoudAshraf97 wants to merge 12 commits into
NVIDIA-NeMo:mainfrom
MahmoudAshraf97:fast-pre-encoder

Commits

Commits on Aug 22, 2026

Commits on Aug 24, 2026