Miles Enterprise Facing Agentic Rl Framework Radixark Anyscale Ray Summit 2026

Summary

The next evolution of AI is not bigger models. It's AI that knows you: your data, your workflows, your customers. Using AI is good. Agents have taken center stage in vLLM and AMD AITER are moving ROCm support beyond simple porting through workload-aware kernel orchestration, with ... Relying on APIs is a straightforward Day 1 solution, but the reality of production AI is that long-term At Lila Sciences, AI research runs on a self-service, cloud-native foundation. At Debugging distributed ML jobs on Kubernetes is difficult because of the visibility gap between failures at the infrastructure layer ... "Github repository: github.com/ vLLM's engine, ecosystem, and contributor base are all growing fast. This talk surveys where the project stands and the roadmap ... "AI coding agents write and test code orders of magnitude faster than humans. The failures are piling up just as fast, and they ... Reinforcement learning is one of the hardest distributed systems problems in AI: training, inference, and environments all running ...