ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-14 07:48:16 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
ik/try_split_offloaded_moe_up_gate
ik_llama.cpp/ggml
History
Kawrakow a2f5614529 Try to split offloaded MoE up/gate up 
It becomes much slower, despite the graph splits looking
OK. Not sure where it bottlenecks.
2025-12-09 10:09:04 +00:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Hadamard transforms for K-cache - CPU only (#1033)
2025-12-04 06:51:11 +01:00
src
Try to split offloaded MoE up/gate up
2025-12-09 10:09:04 +00:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Enable fusion by default (#939)
2025-11-11 10:35:48 +02:00