Mooncake
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Mooncake — a KVCache-centric disaggregated architecture
Why it matters
Tiered KV cache management grounded in a production service
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2407.00079Added in Week 35, 2026 · See that week
On the map — ⑧ Inference Infrastructure line
- Previous stopSarathi-Serve
- This record · stopMooncake
- Next stopColossus goes live