Skip to content

Support AProjQ4 GGUFs: Q4_K dense attention projections; Metal, ROCm and CUDA performance improvements; SSD streaming support for speed-bench; quality-of-life improvements; bugfixes - #621

Closed
GiorgioOppo wants to merge 189 commits into
antirez:mainfrom
GiorgioOppo:aprojq4-dense-attention

Commits

Commits on Aug 31, 2026

Commits on Sep 1, 2026

Commits on Sep 2, 2026