French AI startup ZML launches free software to enhance inference across multiple chip platforms

Jul 8, 2026

AI Summary

ZML, a French AI startup, has introduced ZML/LLMD, a free inference-performance software that supports various open-source large language models on multiple chip architectures. This initiative aims to optimize AI processing speed and reduce vendor lock-in, potentially disrupting the market amid rising AI costs.

ZML is a French AI startup backed by Turing Award winner Yann LeCun, which has launched ZML/LLMD, an inference-performance software.
The software enables open-source large language models to run on various chips, including those from Nvidia, AMD, Google, Apple, and Intel.
ZML's goal is to break down silos in AI chip usage, allowing for optimized performance and efficiency across different hardware.
The startup aims to provide enterprises with the flexibility to utilize a mix of chips, potentially lowering costs and energy consumption.
ZML's founder, Steeve Morin, emphasizes the importance of optimizing inference as AI becomes more integrated into daily life.
The company has raised $20 million from various venture capital firms and is noted for its rapid development pace with a small team of 20.
ZML/LLMD is launching as a free product to gather usage data before potentially transitioning to a paid model.
The startup is seen as part of a broader trend in the AI industry, which has seen significant investment in inference technologies, referred to as the

ai startupinferencesoftwarecost reductionyann lecun

French AI startup ZML launches free software to enhance inference across multiple chip platforms

Related Stories

OpenAI discontinues Atlas but enhances AI browsing features in ChatGPT and Chrome extension

Meta launches Muse Spark 1.1, a new AI coding model to compete in the market

Meta introduces AI image generator, raises concerns over use of public Instagram photos

Meta to Begin Production of New AI Chips in September to Reduce GPU Costs