Executive Summary
- •Volantis raised an $88 million Series A to build AI inference chips using custom optical memory interconnects.
- •The architecture extends wire range from 5mm to 200mm, allowing accelerators to fit more than 220 memory chiplets.
- •The company plans to ship its A-1 data center appliance next year with 10 terabytes of memory and 250 Tbps bandwidth.
Community Sentiment
Key Developments & Data
Get the unfiltered signal before markets open.
Top tech breakthroughs, venture funding, and market moves—synthesized into a 2-minute morning read. Zero PR fluff.
Zubiqo Strategic Assessment
Primary Impact
Data center operators and AI hardware competitors attempting to solve the memory bandwidth bottleneck that limits large language model inference speeds.
Strategic Shift
Moving away from traditional copper interconnect constraints by leveraging cheaper VCSEL-based optical components to physically separate and scale GPU memory modules.
The Ripple Effect
If the A-1 appliance successfully ships with 250 Tbps bandwidth, expect major hyperscalers to accelerate their own internal silicon photonics programs to match the architecture.
This intelligence assessment is generated by Zubiqo's AI for informational purposes only.
Intelligence Quality Rating
Grade this brief: Slide & release to submit rating, or tap a preset.
