Io.github.chrischall/splitwise-mcp version 2.2.1, an MCP server for Splitwise expense and group management, was published to the official MCP registry on 2026-08-22. The server, distributed as splitwi…
Disaggregated LLM serving, which runs prefill and decode on separate GPU pools and transfers KV caches over the network, should always be used in practice under sufficient load, according to a technic…
Prefill/decode disaggregation, which runs LLM prefill and decode phases on separate hardware pools, cut p99 inter-token latency by 66% (from 88ms to 30ms) in a Go simulation, at the cost of higher tim…
A new arXiv paper (arXiv:2607.28633v1) proposes a topology-aware transfer orchestrator for disaggregated GPU inference, claiming existing systems like DistServe, Splitwise, and Mooncake ignore that ba…