diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-19 16:46:23 +0300 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:52 +0300 |
| commit | 58d9e8f1d2efba4b6717043f7a5167be670a6f2e (patch) | |
| tree | bc70f7b1197e9572c3efdfa84d349b729c41cf9b /ggml.c | |
| parent | 927e251a12fa287e13c6bd9667ee97d783486c09 (diff) | |
bitnet: put the scale in a separate tensor
and correspondingly add an extra ggml_mul_mat operation.
As per @ggerganov, this is how things should be done.
It seems to be working, but as far as I can tell this
results in a ~15% performance penalty for prompt processing.
Commiting so I can go and test on othe platforms.
Diffstat (limited to 'ggml.c')
0 files changed, 0 insertions, 0 deletions