News for hackers. Stuff that matters.
Re:Major upgrades to Ray Serve: 88% lower latency and 11.1x ... by djwjjtw on Thursday March 26, 2026 @02:48AM (#47527337)
The real story here is replacing Ray Core's actor task dispatch with direct gRPC for the hot path. Essentially admitting that the general-purpose actor model was the bottleneck for inference workloads. Smart move — let Ray handle orchestration and get out of the way for actual data flow.