Event Overview
PyTorch is the engine that drives flexibility, scalability, and—most importantly—accessibility for every enterprise, regardless of their hardware or cloud provider. To ensure that AI innovation remains democratic, we must protect the user's agency to choose the tools and hardware that best fit their specific needs.
Red Hat® AI is built for fast, flexible, and efficient inference through its vLLM-powered server. It reliably connects models to your data to unify the customization and development of specialized agents on a single platform. Built on an open source foundation, our products give you full control of AI workflows from end-to-end at any scale.
The Red Hat AI portfolio includes Red Hat AI Enterprise, a platform for deploying, managing, and scaling AI inference, agentic AI workflows, and AI-powered applications on any infrastructure.
Visit us at booth P2. Stop by to discuss how PyTorch and Red Hat are building for agency, democracy, and optionality. Plus check out a demo, and grab some swag!
Speaking SessionsOctober, 20, 2026
|
||||
|---|---|---|---|---|
|
10:20am PT |
Keynote: Open Source Inference at Production ScaleBrian Stevens, Senior Vice President and AI CTO, Red Hat |
|||
|
11:45 AM |
A Developer’s Guide to Attention in vLLMMatthew Bonanni, Machine Learning Engineer, Red Hat Lucas Wilkinson, Senior Principal Engineer, RedHat |
|||
|
12:00 PM |
Scaling PyTorch's Compatibility Promise: A Tiered Cross-Repository CI Relay for Out-of-Tree BackendsSubin George, Senior Software Engineer - Red Hat Jewel K M, Principal Software Engineer, Red Hat |
|||
|
2:15 PM PT |
State-of-the-Art KV Transfer for Disaggregated LLM Serving in vLLMZhanqiu Hu, Machine Learning Engineer, Red Hat Nicolò Lucchesi, Research Engineer, Mistral AI Sunita Nadampalli, Principal Engineer, AI/ML, Amazon |
|||
|
3:25 PM PT |
Making Enterprise Agentic Inference Production-Ready with PyTorch and vLLMJoseph Groenenboom, Senior Principal Machine Learning Engineer, PyTorch Architect, Red Hat Tyler Michael Smith, Chief Architect Inference Engineering, Red Hat |
|||
|
3:40 PM |
Gain Geospatial Understanding with the PyTorch EcosystemSteven Pousty, Principal AI Community Architect, Red Hat |
|||
|
4:10 PM |
Quantization Showdown: PyTorch Inference OptimizationMarkell Rawls, Technical Marketing Engineer, Red Hat |
|||
|
October, 21, 2026
|
||||
|---|---|---|---|---|
|
10:35 am |
Contributing to Inference OSS That Won't Stand Still: A BoF on vLLM, llm-d, and the Moving TargetMaroon Ayoub, Senior Principal MLE, Red Hat Nili Guy, R&D Manager and STSM, IBM |
|||
|
12:20pm |
Ecosystem Working Group: Unlocking Community Impact Through the PyTorch LandscapeJoseph Groenenboom, Senior Principal Machine Learning Engineer, PyTorch Architect, Red Hat Chris Hoge, AI Platform Software, NVIDIA |
|||
|
2:15 pm |
Clearing the Path Towards an ABI Stable PyTorch C++ Extension EcosystemSean McGovern, Principal Machine Learning Engineer, Red Hat Chris Leonard, Chris Leonard, PhD, Red Hat Jane Xu, SWE @ PyTorch, Meta |
|||
|
4:30pm |
Prefix Caching for Autoregressive Stages in Multi-Stage PipelinesRicardo Noriega, Principal Software Engineer, Red Hat Alex Brooks, Principal Machine Learning Engineer, Red Hat |
|||
PyTorch, Powering the Enterprise
Day 0 with Red Hat, NVIDIA, and IBM
If you’re building, deploying, or scaling AI in the enterprise, join Red Hat, NVIDIA, and IBM on Oct. 19 for PyTorch, Powering the Enterprise, an in-person event exploring PyTorch and the ecosystem shaping the future of enterprise AI.
PyTorch, and technologies across its ecosystem like vLLM, Ray, and Helion have become foundational to the AI stack, moving from research labs into production at some of the world’s largest enterprises.
You’ll hear from and interact with the companies helping to bring PyTorch to its full enterprise potential, with conversations spanning AI infrastructure, deployment, security, and the open source ecosystem.
Space is limited to 75 attendees.
When: Monday, Oct. 19, 9:00am-3:00pm PT
Where: San Jose, California
Join the conversation