layered-prefill

Layered prefill changes the scheduling axis from tokens to layers and removes redundant MoE weight reloads while keeping decode stall free. The result is lower TTFT, lower end-to-end latency, and lower energy per token without hurting TBT stability. Maintained by scale-snu on GitHub, where it has earned 20 stars from the community.

It's actively developed around llm-serving, vllm, inference, and is a solid reference for anyone building with these tools.