char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Akarshan Biswassycl : add flash-attn support for head size 512 (#21654)b54cb2e3d

char/aliceai-t5-moe
147 B6 linesraw
1// This file has been autogenerated by generate_cu_files.py, do not edit manually.
2
3#include "../fattn-tile.hpp"
4
5DECL_FATTN_TILE_CASE(512, 512);
6