Projects
Explore our open-source projects focused on KVCache optimization and LLM serving.
KTransformers
KTransformers is a CPU/GPU heterogeneous LLM inference and fine-tuning framework for running and tuning 100B+ models on accessible workstation hardware.Made with
Approaching AI !
Mooncake
Mooncake, delicious mooncake made with 
Moonshot AI !
A KVCache-centric disaggregated architecture for LLM serving.