Go behind the scenes of Red Hat's internal innovation engine to discover how we evaluate emerging open source tech and choose exactly where to place our next major technology bets. In this episode of Technically Speaking, Red Hat Chief Technology Officer Chris Wright sits down with Steve Watt, Vice President of the Office of the CTO at Red Hat, for a clear, "200-level" look at what's coming down the road. Together, they map out how Red Hat’s pathfinding group tracks open source innovations and shapes raw clay into enterprise-ready layouts. Steve shares how his teams follow proven open source innovators and build strategic university partnerships to stay ahead of an AI cycle that changes every single week.

Dive into the mechanics of composable intelligence, where the conversation explores the vLLM Semantic Router. This open source project, incubated within Red Hat, allows businesses to selectively route inference requests across specialized small language models or fall back to larger cloud models based on real-time cost, data privacy, and semantic analysis. Chris and Steve also break down how confidential computing protects data, showing how secure enclaves can keep proprietary model weights safe even when running in third-party environments.

Finally, discover how the hardware landscape is moving past GPU scarcity. Learn how new matrix multiplication instructions are opening up inference workloads on modern x86 CPUs, how specialized accelerators like Cerebras, Grok, and IBM Spyre are meeting strict data center power budgets, and how the OpenReg project makes it easier for silicon startups to integrate with PyTorch. Tune in to see why the real enterprise AI secret sauce is no longer just the model itself, but the open source infrastructure backing it.