Subvolts take Inferact's founders explain how to run AI models faster and cheaper with open-source infrastructure. Jan 22, 2026 - Developers
- Learn how to optimize AI model deployment for speed, cost, and reliability using open-source tools.
- Business
- Understand the infrastructure challenges and solutions for efficiently running AI models in production environments.
This episode features the founders of a new AI infrastructure company, offering insights into a critical but often overlooked area of AI deployment.
Inferact: Building the Infrastructure That Runs Modern 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 the founders of Inferact, the creators of vLLM. They discuss building open-source AI inference infrastructure to make large models run faster, cheaper, and more reliably on any hardware. The conversation covers the challenges of AI inference in production and their vision for a universal inference layer.
Running big AI models is hard and expensive. This episode explains how Inferact is building tools to make AI run more efficiently, like making a car engine run better on any type of fuel. This helps everyone use AI more easily.
This episode is for developers and engineers working with AI models in production. It demystifies the complex problem of AI inference, explaining why it's a bottleneck for deploying large language models. The discussion highlights how open-source projects like vLLM are addressing these challenges, which is crucial as frontier labs like Google Gemini and OpenAI scale their model deployments. Understanding inference infrastructure is key to efficient AI operations.
- Hosta16z
- GuestMatt BornsteinInferact
- GuestSimon MoInferact
- GuestWoosuk KwonInferact
- Episode Title: Inferact: Building the Infrastructure That Runs Modern AI
- Show: AI + a16z
- Length: 44 minutes
- Company Founded: Inferact
- Project Origin: vLLM
- Mission: Build a universal, open-source inference layer for AI models.
Inferact is a new AI infrastructure company founded by the creators and core maintainers of vLLM. Its mission is to build a universal, open-source inference layer that makes large AI models faster, cheaper, and more reliable to run across any hardware, model architecture, or deployment environment. Together, they broke down how modern AI models are actually run in production, why “inference” has quietly become one of the hardest problems in AI infrastructure, and how the open-source project vLLM emerged to solve it. The conversation also looked at why the vLLM team started Inferact and their vision for a universal inference layer that can run any model, on any chip, efficiently.
Follow Matt Bornstein on X: https://twitter.com/BornsteinMatt
Follow Simon Mo on X: https://twitter.com/simon_mo_
Follow Woosuk Kwon on X: https://twitter.com/woosuk_k
Follow vLLM on X: https://twitter.com/vllm_project
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
- Woosuk Kwon, Simon Mo, Matt Bornstein
- The process of using a trained AI model to make predictions or generate outputs.
- inference layer
- Woosuk Kwon, Simon Mo, Matt Bornstein
- The software and hardware system that runs AI models to produce results.
24 minHow AI Is Rewriting the Rules of Cybersecurity | Truffle Security & Socket
WithDylan Ayrey, Feross Aboukhadijeh
47 minInside vLLM: The Engine Powering Open-Source AI
WithSimon Mo
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
Same guests, other shows
47 minInside vLLM: The Engine Powering Open-Source AI
WithSimon Mo
1 h 03
1 h 10
1 h 42Davos 2026: The US-China AI Race, GPU Diplomacy, and Robots Walking the Streets | #225
WithSalim Ismail, Dave Blundin, Dr. Alexander Wissner-Gross
1 h 51Claude Code Ends SaaS, the Gemini + Siri Partnership, and Math Finally Solves AI | #224
WithSalim Ismail, Dave Blundin, Alexander Wissner-Gross
Questions people ask
- What is Inferact?
- Inferact is a new AI infrastructure company founded by the creators of vLLM, aiming to build an open-source inference layer for large AI models.
- What problem does vLLM solve?
- vLLM emerged to solve the challenges of running large AI models in production, making inference faster, cheaper, and more reliable across different hardware and environments.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to a16z.