All Updates

All Updates

icon
Filter
Product updates
FuriosaAI launches RNGD AI inference chip for high-performance LLM and multimodal model inference (1)
Machine Learning Infrastructure
Aug 26, 2024
This week:
Funding
Slingshot Aerospace secures USD 30 million in growth capital from Trinity Capital
Digital Twin
Sep 12, 2024
Product updates
Akselos introduces software for FPSO monitoring
Digital Twin
Sep 12, 2024
Product updates
Vertical Aerospace completes first phase of VX4 flight testing
Passenger eVTOL Aircraft
Sep 12, 2024
Partnerships
Turbine and Ono Pharmaceutical reach developmental milestone in oncology research collaboration
AI Drug Discovery
Sep 12, 2024
Partnerships
Sino Biological and BioGeometry partner to optimize protein design using GenAI technology
AI Drug Discovery
Sep 12, 2024
Funding
Sinopia Biosciences raises USD 2.2 million in Phase II SBIR grant funding to accelerate oral mucositis program
AI Drug Discovery
Sep 12, 2024
Regulation/policy
eToro settles for USD 1.5 million with SEC over unregistered trading of certain crypto assets
Retail Trading Infrastructure
Sep 12, 2024
Funding
Amprion raises USD 100,000 in research grant funding from ALS Network to support ALS research and therapy development
Longevity Tech
Sep 12, 2024
Funding
Amprion raises USD 100,000 in research grant funding from ALS Network to support ALS research and therapy development
Precision Medicine
Sep 12, 2024
Funding
Epitopea raises GBP 500,000 in grant funding to develop vaccines and TCR-based therapies
Precision Medicine
Sep 12, 2024
Machine Learning Infrastructure

Machine Learning Infrastructure

Aug 26, 2024

FuriosaAI launches RNGD AI inference chip for high-performance LLM and multimodal model inference (1)

Product updates

  • FuriosaAI, an AI semiconductor company, has launched RNGD, an AI accelerator chip for data center inference. The chip is designed for high-performance LLM and multimodal model inference.

  • RNGD features a non-matmul Tensor Contraction Processor (TCP)-based architecture, a robust compiler optimized for TCP, and 48 GB of HBM3 memory. The chip has a TDP of 150 W compared to 1,000+ W for leading GPUs and can deliver 2,000 to 3,000 tokens per second throughput performance for models with around 10 billion parameters. 

  • RNGD is currently sampling to early access customers, with broader availability expected in early 2025. FuriosaAI claims that RNGD offers a perfect balance of efficiency, programmability, and performance. The company states that RNGD is a sustainable and accessible AI computing solution that meets the industry's real-world needs for inference, with the ability to run models like Llama 3.1 8 billion efficiently on a single card.

Contact us

Gain access to all industry hubs, market maps, research tools, and more
Get a demo
arrow
menuarrow

By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.