All Updates

All Updates

icon
Filter
Product updates
FuriosaAI launches RNGD AI inference chip for high-performance LLM and multimodal model inference
Generative AI Infrastructure
Aug 26, 2024
This week:
Management news
6K Additive awarded project to develop C-103 powder for additive manufacturing
Additive Manufacturing
Sep 27, 2024
Partnerships
WAAM3D partners with Innovative Space Carrier, Cranfield University, and Aichi Sangyo for space transport development
Additive Manufacturing
Sep 19, 2024
Product updates
Akselos introduces software for FPSO monitoring
Digital Twin
Yesterday
Funding
Operant AI raises USD 10 million in Series A funding to boost runtime protection
Next-gen Cybersecurity
Yesterday
Funding
Aembit raises USD 25 million in Series A funding to advance IAM solutions
Identity & Access Management
Yesterday
Product updates
Saviynt launches Intelligence Suite for identity security
Identity & Access Management
Yesterday
Geographic expansion
Partnerships
FarmWise partners with RDO Equipment Co. to expand AI-powered weeding technology for vegetable growers
Smart Farming
Yesterday
Management news
Alberta Food Security Inc. receives USD 5 million order for indoor farming technology
Vertical Farming
Yesterday
Partnerships
AutoStore enhances microfulfilment offering with new grid capabilities and multi-temperature solution
Logistics Tech
Yesterday
Product updates
OpenAI launches o1, a self-fact-checking AI model
Generative AI Applications
Yesterday
Generative AI Infrastructure

Generative AI Infrastructure

Aug 26, 2024

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

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.