Mooncake v0.3.12 adds SSD-backed KV cache pooling and smarter routing
BanghuaZ · x · 2026-07-25
Mooncake v0.3.12 adds major infrastructure upgrades across its store, transfer engine, expert parallelism, and platform support. The release introduces distributed SSD-backed KV cache pooling, smarter intent- and policy-based routing with deadline-aware QoS, wider hardware/platform support, official Docker images, and wheel packages for AWS EFA and MUSA, while also welcoming 53 new contributors.
More from Infra
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- SF Compute founder: buying compute is 'an absolutely awful experience' right now — IgorCarron · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- PyTorch Day Korea 2026 launches first offline conf, CFP closes Sept 13 — PyTorch · 2026-09-11
- Local LLM server dilemma: 4x CMP-170HX (price up 53% in 20 days) vs Mac Studio M5 Ultra — rumboll · 2026-09-11
- llama.cpp lands Flash Attention tuning for RDNA4, big prefill gains on AMD — pmttyji · 2026-09-11