mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-04-02 05:15:38 +02:00
* metal : pad K, V and Mask when needed * cont : simplify * cuda : add TODO about KV padding requirement * metal : add comments * metal : remove mask padding requirement |
||
|---|---|---|
| .. | ||
| cmake | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||