diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-05-09 10:22:48 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 10:22:48 +0300 |
| commit | 8777fc4855dd1551c20a84cb266f75fa49e9b0e8 (patch) | |
| tree | d67ab3b4c004b5043452928147cb3392daa4a828 /convert_lora_to_gguf.py | |
| parent | 496451a1d4c41300ebdb102f12401b8ffa5b1d4b (diff) | |
Fix CUDA FlashMLA-3 with quantized KV cache (#400)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'convert_lora_to_gguf.py')
0 files changed, 0 insertions, 0 deletions