Subvolts take Open-source inference engines like vLLM are becoming essential AI infrastructure, empowering developers. Aug 6, 2026 - Developers
- Learn about vLLM, a powerful open-source tool that can enhance your AI application development and deployment.
- Business
- Understand how open-source inference engines are becoming critical infrastructure, offering control and flexibility for AI deployments.
This episode features a key figure in open-source AI infrastructure, discussing a widely used inference engine.
Inside vLLM: The Engine Powering Open-Source AI
Audio streams from a16z. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
This AI + a16z podcast episode features Simon Mo, co-founder of Inferact, discussing vLLM, an open-source inference engine. They explore the evolution of open-source AI into critical infrastructure, the importance of inference in the AI stack, and how open-source solutions empower developers. The conversation covers open-weight models, AI infrastructure control, and the narrowing gap between open and closed AI models.
This episode talks about vLLM, a powerful engine that helps AI understand and generate text. It explains how this open-source tool is becoming a key part of building AI, making advanced AI more accessible to developers.
This episode offers insight into the critical infrastructure layer of AI development, focusing on inference engines like vLLM. It's for developers and business leaders interested in open-source AI's growing role and the trend towards greater control over AI deployments. Listeners will learn about the economics and technical underpinnings of open-weight models. This connects to frontier labs' efforts to build and deploy large models efficiently, whether through proprietary systems or by enabling open ecosystems.
- Hosta16z
- GuestSimon Moco-founder and CEO, Inferact
- Episode Title: Inside vLLM: The Engine Powering Open-Source AI
- Show: AI + a16z
- Length: 47 minutes
- Guest: Simon Mo, co-founder and CEO of Inferact
- Key Technology: vLLM (open-source inference engine)
Elena Burger and Matt Bornstein are joined by Simon Mo, co-founder and CEO of Inferact, the open-source inference engine powering many of today's most advanced AI applications. Together, they explore how open-source AI evolved from a research project into critical infrastructure, why inference has become one of the most important layers of the AI stack, and what it takes to bring frontier intelligence to developers around the world.
The conversation covers vLLM's origins, the rise of open-weight models, why companies increasingly want control over their AI infrastructure, and how open-source inference enables the next generation of AI applications. They also discuss model licensing, the economics of open-weight AI, Kimi K3, distillation, AI infrastructure, and why Simon believes the gap between open and closed models is rapidly disappearing.
Resources:
Follow Simon Mo on X: https://x.com/simon_mo_
Follow Matt Bornstein on X: https://x.com/BornsteinMatt
Follow Elena Burger on X: https://x.com/VirtualElena
Follow Inferact: https://x.com/inferact
Check out everything a16z is doing with artificial intelligence here, including articles, projects, and more podcasts.
Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.
- inference engine
- Simon Mo
- A system that helps AI process information and generate responses or actions.
- open-weight models
- Simon Mo
- AI models whose underlying structure and parameters are made public, allowing others to use and build upon them.
24 minHow AI Is Rewriting the Rules of Cybersecurity | Truffle Security & Socket
WithDylan Ayrey, Feross Aboukhadijeh
41 minBuilding Self-Accelerating AI with Mirendil
WithBehnam Neyshabur, Harsh Mehta
43 minIdeogram’s Open-Weights Image Model and the Future of AI Design
WithMohammad Norouzi
50 minBuilding Search for AI Agents with Exa CEO Will Bryk
WithWill Bryk
Same guests, other shows
44 minInferact: Building the Infrastructure That Runs Modern AI
WithMatt Bornstein, Simon Mo, Woosuk Kwon
Questions people ask
- What is vLLM?
- vLLM is an open-source inference engine that powers many advanced AI applications, making it a critical piece of AI infrastructure.
- Why is inference important in AI?
- Inference has become a crucial layer of the AI stack, and open-source inference engines like vLLM enable the next generation of AI applications for developers.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to a16z.