French AI startup ZML releases free inference accelerator for multiple chip types
Hot French startup ZML releases free product to speed inference across lots of AI chips
ZML released ZML/LLMD, open-source software that speeds up inference for models like Llama and DeepSeek across Nvidia, AMD, Google TPU, Apple Metal, and Intel Arc chips. Founder Steeve Morin says the goal is cheaper inference, and it's free for now. Turing Award winner Yann LeCun previously endorsed the startup. The post doesn't disclose funding details or benchmark comparisons—I'd wait for real-world numbers before getting excited.
Why it matters: ZML open-sourced its cross-chip inference acceleration tool for free, covering Nvidia, AMD and Google TPU hardware in a bid to cut model inference costs.