mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-08 23:40:10 +00:00
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.
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.