fix: Q1_0_g128 x86 CPU kernel - correct output + AVX2/AVX-512 VNNI#6

Open

stfurkan wants to merge 2 commits intoPrismML-Eng:prismfrom

stfurkan:fix/q1_0_g128-x86-cpu-kernel

Commits on Apr 2, 2026

fix: Q1_0_g128 x86 CPU kernel - correct output + AVX2/AVX-512 VNNI
stfurkan
committed

Commits on Apr 3, 2026

perf: use float accumulator + mul_sum_i8_pairs_float for AVX2 path
stfurkan
committed