Uploaded August 2026 | Updated September 2026, 2 weeks ago
Data scientists know PyTorch as a foundational library for building models, but it's emerged as the primary bridge between raw hardware and enterprise AI runtimes. In this episode of Technically Speaking, Red Hat CTO Chris Wright sits down with Steve Pousty, Principal AI Community Architect at Red Hat, to examine how open source platforms like PyTorch are standardizing data architecture. Discover why PyTorch acts as the modern "kernel" for enterprise AI systems, how distributed serving engines like vLLM and Ray scale inference, and how neutral project governance provides true hardware choice for the data center.
In this episode:
00:00 - Intro: Moving AI from experiment to enterprise production
01:16 - Why PyTorch is the de facto standard library for the AI stack
02:24 - The Linux Kernel analogy: Hardware abstraction layers
05:10 - Under the hood: Abstraction graphs, data libraries, and tensor math
06:00 - Using Python as a Domain-Specific Language for gradient descent
09:08 - Overcoming silicon proliferation with Project Open Ridge
11:32 - The vital role of open source foundation governance
14:05 - Deep dive: Distributed computing clusters with Anyscale Ray
16:08 - Slashing runtime execution overhead by 30% using Helion DSL
16:50 - Production inference: Scaling engines with vLLM and Kubernetes-native llm-d
20:39 - The baseline soil: Building the stack for autonomous agents
Learn More:
Why the future of AI depends on a portable, open PyTorch ecosystem: redhat.com/en/blog/why-future-ai-depends-portable-open-pytorch-ecosystem
Learn more about PyTorch Foundation initiatives: pytorch.org/foundation
Explore Red Hat's open source AI strategy: redhat.com/en/topics/ai
Follow us:
Chris Wright: linkedin.com/in/chris-wright-b733851
Steve Pousty: linkedin.com/in/thesteve0
What is Technically Speaking with Chris Wright?
Technically Speaking with Chris Wright taps into emerging technology trends with insights from leading experts across the globe and Red Hat CTO Chris Wright. The series blends deep-dive discussions, tech updates, and creative short-form content, solidifying Red Hat’s role as a pioneer in technology innovation and open source thought leadership.
Want to participate? Leave us a comment if there's a topic or a guest you'd like to see featured.
Watch More Technically Speaking with Chris Wright:
YT playlist: youtube.com/playlist?list=PLbMP1JcGBmSGfI0Rl4s6PpycLF4rZcfW8
Webpage: redhat.com/en/technically-speaking
Subscribe to Red Hat's YouTube channel: youtube.com/redhat/?sub_confirmation=1
#RedHat #PyTorch #vLLM #AIInfrastructure #OpenSource"
Data scientists know PyTorch as a foundational library for building models, but it's emerged as the primary bridge between raw hardware and enterprise AI runtimes. In this episode of Technically Speaking, Red Hat CTO Chris Wright sits down with Steve Pousty, Principal AI Community Architect at Red Hat, to examine how open source platforms like PyTorch are standardizing data architecture. Discover why PyTorch acts as the modern "kernel" for enterprise AI systems, how distributed serving engines like vLLM and Ray scale inference, and how neutral project governance provides true hardware choice for the data center.
In this episode:
00:00 - Intro: Moving AI from experiment to enterprise production
01:16 - Why PyTorch is the de facto standard library for the AI stack
02:24 - The Linux Kernel analogy: Hardware abstraction layers
05:10 - Under the hood: Abstraction graphs, data libraries, and tensor math
06:00 - Using Python as a Domain-Specific Language for gradient descent
09:08 - Overcoming silicon proliferation with Project Open Ridge
11:32 - The vital role of open source foundation governance
14:05 - Deep dive: Distributed computing clusters with Anyscale Ray
16:08 - Slashing runtime execution overhead by 30% using Helion DSL
16:50 - Production inference: Scaling engines with vLLM and Kubernetes-native llm-d
20:39 - The baseline soil: Building the stack for autonomous agents
Learn More:
Why the future of AI depends on a portable, open PyTorch ecosystem: redhat.com/en/blog/why-future-ai-depends-portable-open-pytorch-ecosystem
Learn more about PyTorch Foundation initiatives: pytorch.org/foundation
Explore Red Hat's open source AI strategy: redhat.com/en/topics/ai
Follow us:
Chris Wright: linkedin.com/in/chris-wright-b733851
Steve Pousty: linkedin.com/in/thesteve0
What is Technically Speaking with Chris Wright?
Technically Speaking with Chris Wright taps into emerging technology trends with insights from leading experts across the globe and Red Hat CTO Chris Wright. The series blends deep-dive discussions, tech updates, and creative short-form content, solidifying Red Hat’s role as a pioneer in technology innovation and open source thought leadership.
Want to participate? Leave us a comment if there's a topic or a guest you'd like to see featured.
Watch More Technically Speaking with Chris Wright:
YT playlist: youtube.com/playlist?list=PLbMP1JcGBmSGfI0Rl4s6PpycLF4rZcfW8
Webpage: redhat.com/en/technically-speaking
Subscribe to Red Hat's YouTube channel: youtube.com/redhat/?sub_confirmation=1
#RedHat #PyTorch #vLLM #AIInfrastructure #OpenSource"
