Volantis raises $88 million to develop AI chip-to-memory interconnect technology

Traders Union
All News
Financial News
Volantis AI chip interconnect

Highlights

Volantis raised $88 million in venture capital to develop laser-based chip-to-memory interconnects targeting a core AI hardware limitation.
The company plans to deliver a chip in 2025 using VCSELs technology, potentially linking up to 220 memory chips per GPU and addressing supply chain bottlenecks.
Investors in the round include Lachy Groom, Abstract Ventures, John Doerr, VXI Capital, Triatomic, Susa Ventures, and notable angel backers.

Funding backs optical chip link plan

As reported by Reuters, San Francisco-based Volantis said on Thursday it has raised $88 million in venture capital to tackle a core limitation in AI chips, the connection between computing processors and memory components.

The company says current designs from Nvidia and Advanced Micro Devices rely on expensive high-bandwidth memory placed around computing chips, but the reach of electrical wiring limits how many memory chips can be connected. Volantis is developing a system that uses laser beams to send data between computing chips and memory chips, which it says would allow as many as 220 memory chips around a GPU.

Chief executive and co-founder Tapa Ghosh said the company is combining established components rather than depending on unproven breakthroughs. He said Volantis aims to deliver a chip next year that would accelerate tasks such as AI coding while avoiding some supply chain bottlenecks tied to advanced AI hardware.

Investors target AI hardware bottlenecks

The startup's design uses vertical-cavity surface-emitting lasers, or VCSELs, a technology already used in facial recognition systems in many Apple devices. Volantis is betting that using components with an existing manufacturing base can reduce some of the constraints that affect development of new AI chips.

The funding round was led by Stripe veteran Lachy Groom and Abstract Ventures. The investor group also includes John Doerr, VXI Capital, Triatomic and Susa Ventures, along with angel investors Dwarkesh Patel, Naveen Rao and Anthropic researcher Sholto Douglas.

Micron’s latest results highlighted how AI-driven DRAM and NAND demand continues to outstrip supply, supporting higher pricing and extending strong earnings momentum into the next fiscal years. Our earlier article noted that Micron expects tight conditions to persist into 2027–2028, with a large portion of future output already committed, underscoring how memory constraints remain a key chokepoint for the broader AI hardware market.

This material may contain third-party opinions, none of the data and information on this webpage constitutes investment advice according to our Disclaimer. While we adhere to strict Editorial Integrity, this post may contain references to products from our partners.