#706 Feat/q2 avx2 bitplane

closed · @merbanan · 0 评论 · 在 GitHub 查看

描述

A new AVX2 row kernel for Q2_0 experts on CPUs without AVX-512, the default path in `q2_0_gguf_rows_multi_avx2`.

**Single thread, weights in L2:** 2.3–2.8× faster at every token count from 1 to 4.

站内延伸阅读

Install Strata
Model sizes & RAM
Release notes

链到安装、模型与版本说明，便于 SEO/GEO，非官方 issue 正文。