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
- Bittensor TAO ecosystem map lays out dozens of AI subnets across compute, agents, and security — 0xSammy · 2026-07-25
- Enterprise user asks which models can cut frontier-token spend on a $1M compute budget — mimic751 · 2026-07-25
- The AI chip startup map has swelled to about $58B in private-paper value — deedydas · 2026-07-25
- A local LLM user weighs a 16GB AMD GPU against a second RTX 3090 — kobbalt · 2026-07-25
- SpaceX says Starship V3 is improving reusable orbital heat-shield tiles flight by flight — XFreeze · 2026-07-25
- A $8.5B conversational frontier is exposing the real cost of the AI boom — Some-Technology4413 · 2026-07-25