Skip to content
  • Categories
  • Newsletter
  • Recent
  • AI Insights
  • Tags
  • Popular
  • World
  • Groups
Skins
  • Light
  • Brite
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
  1. Home
  2. AI Insights
  3. AI Chip Startup Taalas Secures $50 Million Funding for Custom Chips to Power AI Models
uSpeedo.ai - AI marketing assistant
Try uSpeedo.ai — Boost your marketing

AI Chip Startup Taalas Secures $50 Million Funding for Custom Chips to Power AI Models

Scheduled Pinned Locked Moved AI Insights
ai-articles
1 Posts 1 Posters 4 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • baoshi.raoB Offline
    baoshi.raoB Offline
    baoshi.rao
    wrote last edited by
    #1

    According to SiliconANGLE, AI chip startup Taalas, led by Tenstorrent founder Ljubisa Bajic, has successfully raised a total of $50 million in two funding rounds to develop customized chips for specific AI models. Image source note: The image is AI-generated and licensed by Midjourney.

    Ljubisa Bajic, who previously worked at AMD and Nvidia, was the founder and first CEO of Tenstorrent. In October 2022, he transitioned to the role of CTO and president at Tenstorrent, handing over the CEO position to renowned chip designer Jim Keller. In March 2023, Ljubisa Bajic left Tenstorrent and founded the new company Taalas in September.

    Taalas aims to build highly specialized chips to provide customized computing power for AI models. The company believes that commoditizing AI requires increasing computing power and efficiency by 1000 times, a goal unattainable with general-purpose computing solutions. Only by tightly integrating chips and models can sustainable development be achieved. Taalas' chips are designed specifically for neural network requirements, eliminating the need for external memory and accommodating entire models on-chip. Utilizing efficient hardwired computing, a single chip can rival small GPU data centers.

    Taalas plans to complete the tape-out of its first LLM chip in the third quarter of this year and aims to ship to early customers in the first quarter of 2025. Through customized dedicated chips, Taalas is committed to promoting the widespread adoption of AI in daily life and providing strong support for the development of AI models.

    1 Reply Last reply
    0
    Reply
    • Reply as topic
    Log in to reply
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes


    • Login

    • Don't have an account? Register

    • Login or register to search.
    • First post
      Last post
    0
    • Categories
    • Newsletter
    • Recent
    • AI Insights
    • Tags
    • Popular
    • World
    • Groups