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 iconApproaching AI !

Mooncake


Mooncake, delicious mooncake made with iconMoonshot AI !

A KVCache-centric disaggregated architecture for LLM serving.

AgentENV


A scalable sandbox infrastructure platform for AI agents, providing secure, isolated, and rapidly forkable Firecracker microVMs for training and production workloads.