((Automated translation by Reuters using machine learning and generative AI, please refer to the following disclaimer: https://bit.ly/rtrsauto))
Tensordyne said Monday it expects more than $200 million in orders for its new inference system, as the AI chip startup positions itself as a direct competitor to Nvidia NVDA.O in a growing but increasingly power-hungry market.
Its Tensordyne Napier chip, developed in collaboration with Broadcom AVGO.O and Juniper Networks HPE.N (a subsidiary of HPE), is manufactured by TSMC 2330.TW, the world’s leading contract chip manufacturer.
Headquartered in Sunnyvale, California, the company aims to alleviate AI infrastructure constraints by improving inference speed, power efficiency and rack density amid a surge in demand for generative AI.
Chief executive Marc Bolitho told Reuters the product is expected to be officially launched in the coming months and that there is “strong interest” in the startup.
“We have received more than a dozen letters of intent from companies interested in evaluating our beta systems and we anticipate demand for more than $200 million in the future,†he said.
The company said AI infrastructure providers Cirrascale and BlueSky Compute had expressed interest in the system, alongside large technology companies and AI cloud service providers.
Founded in 2017 as Recogni, the company changed its name to Tensordyne last year. It has raised around $176 million from investors including Celesta Capital, GreatPoint Ventures and Juniper Networks, and is gearing up for a Series D funding round later this year.
