French Startup ZML Releases Free Inference Server Compatible Across AI Chips

emmanuelvivier · x · 2026-07-29

ZML, a French AI startup endorsed by Turing Award winner Yann LeCun, has launched ZML/LLMD, a free LLM inference server.

The software aims to break vendor lock-in by allowing various open-source large language models to run at peak performance across a wide range of chips, including Nvidia, AMD, Google TPU, Apple Metal, and Intel Arc. The founder noted that as inference demand surges, cross-chip optimization will be key to disrupting the market.

Related event: ZML Releases Free Inference Server Across Multiple AI Chips(3 posts)→

Original post →

More from Infra

Infra channel →