GitHub · Python
ewhacc/tandem.cpp
llama.cpp patch: faster MoE offload for models that don't fit in VRAM
- Stars
- 107
- Forks
- 19
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: gguf, inference-engine, llama-cpp, local-llm, moe
Latest data point: Nov 20, 2026 · 107 stars · 19 forks