Prefix Cache and Multi-Tier Caching

5.20.1Prefix Caching with Radix-Tree/Hash Indexing#

5.20.2Cache-Aware Scheduling and Prefix Locality#

5.20.3HiCache: HBM, Host DRAM, and External Storage#

5.20.4LMCache, Mooncake, and Shared KV Storage#

5.20.5Cache Prefetch, Migration, and Asynchronous Write-Back#

5.20.6Cache Coherence Across Processes, Devices, and Nodes#

5.20.7Multi-Tenant Cache Isolation and Invalidation Management#