diff options
| author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-18 20:08:28 +0300 |
|---|---|---|
| committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-22 12:02:52 +0300 |
| commit | 927e251a12fa287e13c6bd9667ee97d783486c09 (patch) | |
| tree | 90ed8827fc28630f52e92d8b8ea664198a6f5829 /llama.cpp | |
| parent | 181fd9c56eaa64d0a92f9e8be7387f409cfa8745 (diff) | |
Bitnet(1.75 bpw): higher precision fp8 scale
Use 3 bits for the exponent and 5 bits for the mantissa.
This makes PPL to be the same as fp16 (but the previous
version with 4 bits for the exponent and mantissa was
good enough for any practical purposes).
Diffstat (limited to 'llama.cpp')
0 files changed, 0 insertions, 0 deletions