diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2023-06-19 18:17:03 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-19 18:17:03 +0300 |
| commit | cb40dfca694b5cb849837548fd69932117c78362 (patch) | |
| tree | 92864fc0f78969e2660deca2b34b07f882f07703 /examples/perplexity/perplexity.cpp | |
| parent | ca7c3f4da5d144d4cd1dd44903552e6ba49b8ec8 (diff) | |
llama : only use Q6_K for output weights if tensor size is multiple of 256 (#1932)
* Only use Q6_K for output weights if tensor size is multiple of 256
* Fixed copy/paste mistake
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/perplexity/perplexity.cpp')
0 files changed, 0 insertions, 0 deletions