Volantis says its optical approach targets AI's memory bottleneck by boosting both memory bandwidth and capacity per chip by orders of magnitude, enabling inference speeds up to 10,000 tokens per second per user for models larger than 10 trillion parameters at low cost per token. The company claims applications including coding agents finishing in minutes or seconds, and argues optics scales across generations rather than 2X per year. The team cites prior work on the first CoWoS product, early HBM, silicon photonics CPO systems, and tunable VCSELs; a next iteration is taped out targeting record bandwidth density.

AI summary of the linked source — not editorial content.

Story signal · how it spread on X · via Elfa

as of
thread quiet
Spread
i
Distinct X and Telegram accounts Elfa counted behind this story’s reports, summed over the thread. Not posts, not impressions.
16 accounts

first post
Leviathan 7.4 h before Elfa saw any post

Thread · 1 event
  1. Leviathan published this article
  2. First reportVolantis raises $88M Series A to build photonic AI memory chips16 acc.

All times UTC.

Cited posts

  • @StockSavvyShay Shay BoloorFirst reportOn X ↗

    Volantis just raised $88M from investors including $GOOGL Jeff Dean to build optical AI chips that ease the memory bottleneck in inference. Interesting timing right after $MU’s record quarter with Volantis betting light can make agent workloads dramatically faster. https://t.co/7MG6s1fjjZ

  • @exec_sum Exec SumOn X ↗

    NEWS: Volantis Semiconductor raised an $88M Series A, led by Abstract Ventures and Lachy Groom, bringing total funding to $97M Other backers include Sam Altman, Dylan Patel, Jeff Dean, and John Doerr. The company is building photonic memory systems designed to tackle AI’s… https://t.co/ZSqupd5RcR

  • @wallstengine Wall St EngineOn X ↗

    Volantis Semiconductor raised an $88M Series A, bringing total funding to $97M, to attack AI’s memory bottleneck with photonics. Backers include: OpenAI's Sam Altman SemiAnalysis'S Dylan Patel Jeff Dean John Doerr and others The company is building an optical “fabric”… https://t.co/4LUwvmpWVZ

Show 3 more cited posts
  • @hasantoxr Hasan ToorOn X ↗

    Volantis raised $88M to fix the part of AI chips that is holding everything back: memory. Their bet is optics. Connect far more memory to each chip with light instead of copper, and push both bandwidth and capacity up by orders of magnitude. The target is 10,000 tokens/sec per… https://t.co/gXBFf1RVu4

  • @alifarhat79 Not Jerome PowellOn X ↗

    Volantis just raised $88M to solve AI’s memory problem with literal light. 10,000 tokens/sec. 10T+ models. Agents that finish in seconds, not hours. Apparently the next AI scaling law is: turn the RAM into a laser beam. https://t.co/Za0EIH3YIV

  • @rohanpaul_ai Rohan PaulOn X ↗

    This team is working to bring a MASSIVE 10,000 tokens/second/user on models above 10T parameters. Volantis wants to cut coding-agent runs from 30 minutes to 30 seconds by feeding AI chips memory over light. Sam Altman, Jeff Dean and John Doerr are among the backers of the $97M… https://t.co/hvUvBzCaGH

10 more accounts posted about this

Social-monitoring data, not investment advice Elfa post text from Xas of

Explore the topic

Loading related coverage…

Explore the full feed

Comments

Loading comments…