Skip to content

Performance and simplification: per-call floor, scrambled layouts, AVX-512 GEMM peak, degenerate shapes, compile latency - #10

Merged
lkdvos merged 65 commits into
mainfrom
integration/perf
Sep 28, 2026
Merged

Performance and simplification: per-call floor, scrambled layouts, AVX-512 GEMM peak, degenerate shapes, compile latency#10
lkdvos merged 65 commits into
mainfrom
integration/perf

Keep the MV = 2 real tile on AMD AVX-512 (znver4/znver5)

456c748
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar