Skip to content

CUDA: faster prompt processing for 4-bit quants#713

Merged
ikawrakow merged 2 commits intomainfrom
ik/cuda_use_bperm
Aug 21, 2025
Merged

CUDA: faster prompt processing for 4-bit quants#713
ikawrakow merged 2 commits intomainfrom
ik/cuda_use_bperm

Commits

Commits on Aug 21, 2025