Files
ik_llama.cpp/include
Kawrakow 63d0389e18 WIP split mode attn
Works for LlaMA models, but not for GLM-4.5.
Doesn't seem to improve performance, so I guess no point in trying to
fix it.
2025-12-01 09:34:14 +00:00
..
2025-12-01 09:34:14 +00:00