News

Latest from VSORA

Articles

February 27th, 2025 – SemiWiki

The Double-Edged Sword of AI Processors: Batch Sizes, Token Rates, and the Hardware Hurdles in Large Language Model Processing

April 17th, 2024 – SemiWiki

CEO Interview: Khaled Maalej, VSORA Founder and CEO

February 12th, 2024 – All About Circuits

AI Inferencing in Data Centers: Breaking the Efficiency-Cost Tradeoff

January 23rd, 2025 – DesignNews

A closer look at LLM’s hyper growth and AI parameter explosion

December 24th, 2024 – EE Times

Hidden Cost of AI: Why Data Center Strategies Need a Rethink

December 24th, 2024 – EE Times Europe

Transformers: Autopilot’s Secret Weapon

November 6th, 2024 – DesignNews

Unlocking Efficiency: Key Requirements for Effective AI Inference

June 24th, 2024 – EE Times Europ

Competing for Supremacy: Strategies to Dominate the AI Accelerator Market

March 11th, 2024 – EE Times

Meeting Challenges Posed by AI Inference at the Edge

January 2024 – DENA

A solution to knock down the memory wall

December 19th, 2023 – Electronic Design

11 Myths About Generative AI

Flexibility

Fully programmable

Algorithm agnostic

Host processor agnostic

RISC-V cores to offload host
& run AI completely on-chip.

Explore Jotunn 8

Memory

Capacity

HBM: 288GB

Throughput

HBM: 8 TB/s

Explore Jotunn 8

Performance

Tensor core (dense)

FP16: 800 Tflops
FP8: 3200 Tflops

General Purpose

FP32: 25 Tflops
FP16: 50 Tflops
FP8: 100 Tflops
Close to theory efficiency

Explore Jotunn 8

Explore Jotunn 8

Introducing the World’s Most Efficient AI Inference Chip.