diff options
author | Kawrakow <iwankawrakow@gmail.com> | 2025-03-18 15:40:47 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-03-18 15:40:47 +0100 |
commit | 68a5b60408b1085d2b2ed5de75e004ee23f8ddb9 (patch) | |
tree | cecd9be0307e484346f4bd65ebe5ff4d34afef9c /examples/eval-callback | |
parent | f4ebf13b6a63ac1367bc392e24566d71c0b4c5b9 (diff) |
Make Q8_0 KV cache work with mla=2,fa on CUDA (#264)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/eval-callback')
0 files changed, 0 insertions, 0 deletions