kvcache-ai/Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

语言：C++ · GitHub 星标：6,994 · Fork：1,445

话题：disaggregation · inference · kvcache · llm · rdma · reinforcement-learning · sglang · tokenspeed

在 GitHub 上查看原仓库