diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-06-13 07:58:15 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-13 07:58:15 +0300 |
| commit | 066ed4fd1158ddaab0080ef0e77bd5b7e12ec114 (patch) | |
| tree | 42707c91f1e27486ffe2e3b4dc974c6694760263 /ggml/src/ggml-kompute.cpp | |
| parent | f72983f7fe16f02cda4af40172b87ff721920b46 (diff) | |
Faster CPU prompt processing for Q4_K and Q5_K (#525)
* q4_K: dequantize to q8_1_r8 for batch >= 32
We get 268 t/s, up from 186 t/s.
* q4_K: GEMM with q8_2_X4
* q5_K: GEMM with q8_2_X4 and repack to q8_1_r8
* Remove the scales, they are not needed
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/ggml-kompute.cpp')
0 files changed, 0 insertions, 0 deletions