Popular repositories Loading

1. llama-wackMall llama-wackMall Public

   Caching experts made model agnostic for llama. Drastically speeds up generation speed on MoE models that fully fit in the RAM but partially in Vram. WIP: Same speedup but for models that don't fit …

   C++ 22 3

2. MFFS_Classic MFFS_Classic Public

   Forked from BuiltBrokenModding/MFFS_Classic

   Classic version of Claclavia's MMFS mod

   Java

3. ThermalIntegration ThermalIntegration Public

   Forked from CoFH/ThermalIntegration

   More phytogenic recipes for mystical agriculture

   Java

4. llama.cpp-wackMall-merge-request llama.cpp-wackMall-merge-request Public

   Forked from ggml-org/llama.cpp

   LLM inference in C/C++

   C++ 1

5. SynaPsi SynaPsi Public

   Project SynaΨ — Its MoE, but an expert can just be a calculator Defensive publication 2026-08-20.