diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-22 12:00:22 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-22 12:00:22 +0100 |
| commit | 3d732cb0109ec936c01c54716c0cd9ef81c808b0 (patch) | |
| tree | 66b99fe24bd114ec2cf8ef91a81dd67e113162cd /ggml/src/ggml-quants.c | |
| parent | 907cde6be257d295e720cece8b8fb999072befa1 (diff) | |
Faster R4 legacy quants (#158)
* q4_0_r4(avx2): convert q8_1 scales with SIMD instrinsics
PP-512 goes to 283 t/s from 265 t/s
* qx_0_r4(AVX2): convert scales with SIMD instrinsics
Also fix q8_0_r4 to not overflow.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-quants.c')
0 files changed, 0 insertions, 0 deletions