GitHub · Python
ewhacc/tandem.cpp
llama.cpp patch: faster MoE offload for models that don't fit in VRAM
- Stars
- 112
- Forks
- 19
- Stars gained in 24 hours
- +24
- Forks gained in 24 hours
- +5
Topics: gguf, inference-engine, llama-cpp, local-llm, moe
Latest data point: Nov 21, 2026 · 112 stars · 19 forks