Skip to content

Pack each IQ weight once and decode the IQ formats on CUDA - #2604

Merged
cjluo-nv merged 2 commits into
mainfrom
chenjiel/iq-export-reuse-cuda-decode
Oct 2, 2026
Merged

cjluo-nv merged 2 commits into
mainfrom
chenjiel/iq-export-reuse-cuda-decode

Commits

  1. Commits on Oct 1, 2026