אודות פרק זה
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.
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.
אנגלית
ארצות הברית
בפרק זה
תעתיק 🔗
Are you the producer of this podcast?
Add a podcast transcript
Need Audio-to-Text?
Transcribe with Listen411 in Just 60 Seconds
חיפוש פרקים ישנים
חפש פרקים קודמים של Technically Speaking with Chris Wright.
פרקים אחרים בפודקאסט הזה
Explore what it takes to run massive language models efficiently with Red Hat's Senior Principal Software Engineer in AI Engineering, Nick Hill. In this episode, we go behind the headlines to uncover the systems-level engineering making AI practical, focusing on the pivotal challenge of inference …
We often hear about AI's potential to generate text and code, but its application in healthcare and life sciences promises a more profound impact: solving our most fundamental challenges in disease and medicine. This isn't just about applying existing LLMs; it's about building entirely new foundat…
Scaling LLM inference for production isn't just about adding more machines, it demands new intelligence in the infrastructure itself. In this episode, we're joined by Carlos Costa, Distinguished Engineer at IBM Research, a leader in large-scale compute and a key figure in the llm-d project. We dis…
The software supply chain has always been a critical battleground, but AI introduces an exponential increase in scale and complexity. We are no longer just securing lines of code; we are now responsible for securing the models that generate it. This a new reality that shifts the entire attack surf…
As modern IT systems grow too complex for humans to effectively manage, there's growing interest in turning to autonomous AI agents for operations. While powerful, these agents introduce new challenges around trust, reliability, and control. To explore how to solve for this, Red Hat CTO Chris Wrig…
הצהרה: הפודקאסט והגרפיקה המוטבעים בדף זה הם מ-Red Hat, שהוא רכושו של בעליו ואינו קשור או מאושר על ידי Listen Notes, Inc.
