Volantis Raises $88M to Build New Chip Architecture for AI Inference
The San Francisco semiconductor startup says its A-1 system could support models above 20 trillion parameters while cutting inference costs per token.
AfroEuropa Newsroom
AfroEuropa desk
Volantis, a San Francisco-based semiconductor company, has raised $88 million in a Series A round to develop a new architecture aimed at AI inference, Ventureburn reported.
The financing was co-led by Lachy Groom and Abstract Ventures, with participation from John Doerr, VXI Capital, Triatomic and Susa Ventures. Angel investors Dwarkesh Patel, Naveen Rao and Sholto Douglas also took part.
The company is addressing a central constraint in AI infrastructure. Large models require both substantial memory capacity and high bandwidth during inference, and current designs force a trade-off between the two. On-chip SRAM delivers high bandwidth but limited capacity, while GPU systems use high-bandwidth memory for greater capacity, though bandwidth can restrict how quickly very large models run.
Keep reading
NVIDIA Adds 64 GB DGX Spark Desktop AI Config With Six Hardware Partners
NVIDIA is rolling out a 64 GB unified memory version of its DGX Spark desktop AI systems through Acer, ASUS, Dell, Gigabyte, HP and MSI, with Gigabyte's variant set for October 23.
Other highlights
Samsung Galaxy S26 FE Gets First Discount as S27 Production Nears
The newly launched Galaxy S26 FE receives its first price cut, while reports from Korea point to mass production starting for the Galaxy S27 range.
Follow the story
One newsletter, two continents
The Bridge brings you the tech, startups, and leaders moving between Africa and Europe in one sharp email each morning. No spam, unsubscribe anytime.
