How Open-Source AI Inference Became Critical Infrastructure: a16z Podcast
a16z Podcast · rss · 2026-08-06
The a16z Podcast hosts Inferact co-founder and CEO Simon Mo to discuss how open-source AI evolved from a research project into critical infrastructure.
Key topics include:
- The Rise of Open-Source Inference: Exploring the origins of vLLM and why inference has become one of the most important layers in the AI stack.
- Infrastructure Control & Economics: Why companies increasingly want control over their AI infrastructure and the economics behind open-weight models.
- Closing the Gap: Discussions on model licensing, distillation, and how open-source inference empowers the next generation of AI applications. Mo argues the capability gap between open and closed models is rapidly disappearing.
More from Infra
- Nebius Inference Platform Hits Milestone in Artificial Analysis Accuracy Index — demian_ai · 2026-08-06
- Run MiniMax Video on 12GB VRAM: 3 Mins per 5s Clip with Audio — BeginningSpiritual49 · 2026-08-06
- Cloudflare Emerging as the Agent Cloud via Rapid Iteration and Weird Bets — threepointone · 2026-08-06
- PlanetScale Details Massively Parallel Backups: Restoring PB-Scale Databases at 50GB/s — bibryam · 2026-08-06
- Calling for Decentralized AI: From the Cloud Back to a $5K Local Personalized AGI — Dan_Jeffries1 · 2026-08-06
- Maple 20B Hits 9,885 tokens/s on a Single NVIDIA GH200 in Concurrency Test — MaziyarPanahi · 2026-08-06