git/ik_llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
ik/fattn_work_buffer
ik_llama.cpp/ggml
History
Iwan Kawrakow 20d50172d0 Much better FA TG with q8_0 KV cache 
Just repack it even for TG. But do the repacking for k_step rows,
not the whole K tensor.
2025-04-28 11:26:28 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Add copyright notices (#317) 2025-04-07 10:43:26 +02:00
src Much better FA TG with q8_0 KV cache 2025-04-28 11:26:28 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Compile time option to use bf16 for qunts without MMQ kernels (#261) 2025-03-18 07:37:10 +01:00