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)→
More from Infra
- AI capital is still flowing, but smaller open-weights and inference bets may be easier to fund — vaibhavbetter · 2026-07-29
- vLLM plans its first Taiwan meetup around GPU optimization and local LLM deployment — vllm_project · 2026-07-29
- UK datacentres may need upfront grid fees as 315 projects queue for 73 GW of power — nordicinst · 2026-07-29
- PrunaAI open-sources a video decoder for LTX-2.3 that cuts VRAM in half — linoy_tsaban · 2026-07-29
- Google posts first quarter of negative free cash flow after years of growth — michalmalewicz · 2026-07-29
- South Korea’s AI-linked stocks sink 10.84% as Samsung and SK Hynix plunge — emmanuelvivier · 2026-07-29