Semiconductor startup Volantis has raised $88 million in Series A funding for a new AI inference architecture built around photonic memory connections. The company announced the financing on October 1, with Lachy Groom and Abstract Ventures co-leading.
Its planned A-1 system targets a persistent computing constraint: supplying large models with enough memory capacity and bandwidth at the same time. Volantis proposes optical links that pool memory chips and increase available bandwidth as more memory is added.
The company aims to support models exceeding 20 trillion parameters at up to 10,000 tokens per second per user. Those figures describe design targets for a system still under development, rather than independently verified customer performance.
Volantis plans initial customer deliveries in 2027. The funding will support engineering and commercialization, drawing on a founding team with experience at Nvidia, AMD, Broadcom and Ayar Labs. Its optical links use custom miniature lasers called micro-VCSELs.
AIstify has previously covered Nvidia’s photonics investments, highlighting how moving data is becoming as important as adding compute. Volantis brings that challenge to the processor-memory connection, where commercial deployment will test whether its proposed architecture can deliver the promised gains.
Disclaimer: AIstify is an independent media brand owned and operated by NuvexMedia LLC, publishing news, research, and insights on artificial intelligence, emerging technologies, automation, and related industries. NuvexMedia LLC invests in and collaborates with companies across the AI, technology, software, and digital innovation sectors. These relationships do not influence AIstify’s editorial coverage, and the publication maintains full editorial independence to provide accurate, timely, and objective information. © 2026 NuvexMedia LLC. All rights reserved. This content is for informational purposes only and should not be considered legal, tax, investment, financial, or other professional advice.
