ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-06 12:00:29 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
001abccf73e51266549438c3b64bb4badc69fc2a
ik_llama.cpp/ggml
History
Iwan Kawrakow 001abccf73 Fusing MoE up * unary(gate): CUDA 
We get ~13% speedup for PP-512 and ~2% for TG-128
for DeepSeek-Lite
2025-02-23 11:37:31 +02:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Fusing MoE up * unary(gate)
2025-02-23 11:37:31 +02:00
src
Fusing MoE up * unary(gate): CUDA
2025-02-23 11:37:31 +02:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
FA: Add option to build all FA kernels (#197)
2025-02-09 18:59:33 +02:00