diff options
author | Kawrakow <iwankawrakow@gmail.com> | 2025-07-02 09:27:47 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-07-02 09:27:47 +0200 |
commit | 3248a3599275c3d2a98bc41d512e1d3ba66e32ba (patch) | |
tree | 14bdaae22a6db922aa9eb0a7131141da81dfd251 /src/unicode.cpp | |
parent | 46f2e5d249568b6395d17a80feb2ba9ab48156e5 (diff) |
Adding IQ3_KS quants (#566)
* iq3_ks: basics
* iq3_ks: CUDA dequantize
* iq3_ks: CUDA mmvq
* iq3_ks: mmq
* iq3_ks: faster mmq
* iq3_ks: Zen4
* iq3_ks: AVX2 convert to q8_k_r8
This gives usPP-512 = 360 t/s.
* iq3_ks: AVX2 GEMM/GEMV
* iq3_ks: NEON GEMM/GEMV
* iq3_ks: NEON convert to q8_k_r8
This gives us PP-512 = 164 t/s.
* iq3_ks: Metal dequantize
* iq3_ks: Metal gemv - pathetic performance
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'src/unicode.cpp')
0 files changed, 0 insertions, 0 deletions