ZML, a French AI startup endorsed by Turing Award winner Yann LeCun, has released ZML/LLMD, a free inference-performance software that allows open source large language models to run on chips including Nvidia’s, AMD’s, Google’s TPU, Apple Metal, and Intel Arc. Founder Steeve Morin told TechCrunch the goal is to break silos and make different chips available at maximum speed, potentially disrupting the market amid AI cost concerns. ZML hopes enterprises and clouds can use a mix of chips that may be less costly or consume less energy. Morin noted the software may help novel AI chipmakers, citing Axelera, Fractile, Kalray, OLIX, Q.ANT, SiPearl, SpiNNcloud, and VSORA. He said ZML has a good relationship with Nvidia. Competitors include Baseten, recently valued at $13 billion; Inferact; and RadixArk. Morin credited ZML’s lean team of 20 people for moving fast. The Paris-based startup raised $20 million from venture firms including Harry Stebbings’ 20VC, >commit, AALVC, Drysdale Ventures, Xavier Niel’s Kima Ventures, Kindred Capital, LocalGlobe, and Puzzle Ventures.