diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2023-07-25 13:48:04 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-07-25 13:48:04 +0300 |
| commit | 129d844c87d90e74aafc23dcc84c980fd408def4 (patch) | |
| tree | 7f47d3436ac64384eaf6f548f3f2406b38fce39d /llama.h | |
| parent | d5512b782b27ff698007dcd175da18959d5f163f (diff) | |
Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)
* Fix Q4_K and Q5_K for QK_K = 64
* Very slightly better Q5_K bit fiddling
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'llama.h')
0 files changed, 0 insertions, 0 deletions