diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-07-30 16:57:39 +0300 |
|---|---|---|
| committer | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-08-01 09:38:06 +0200 |
| commit | 0d19d19af88a508ee8987abe5fc4f8fcaaa1dc2d (patch) | |
| tree | a6cd8b8ec2ad6f10cb252f2ad07a0356c2472bae /ggml/src/ggml-blas.cpp | |
| parent | 4f237d44f6d75afbb5cef39d4d6b0b35b2a517c7 (diff) | |
iq3_k: CUDA dot product
Slightly slower than iq3_s - 132 t/s vs 138 t/s for
LLaMA-3.1-8B.
Diffstat (limited to 'ggml/src/ggml-blas.cpp')
0 files changed, 0 insertions, 0 deletions