--- title: "Hierarchical KV Caching (HiCache)" metatags: description: "SGLang HiCache: three-tier KV caching (GPU, CPU, storage) for long-context and multi-turn inference. Supports Mooncake, 3FS, NIXL backends." --- - [Hicache Best Practices](./hicache_best_practices) - [Hicache Design](./hicache_design) - [Hicache Storage Runtime Attach Detach](./hicache_storage_runtime_attach_detach)