All Updates

All Updates

icon
Filter
Product updates
Syntiant Corp. announces optimizations to run LLMs with high efficiency
Generative AI Infrastructure
Jan 8, 2024
This week:
Funding
zkPass raises USD 12.5 million in Series A funding
Enterprise Blockchain Solutions
Yesterday
Partnerships
Ontada partners with Microsoft to process unstructured oncology data using Azure AI
Clinical Trial Technology
Yesterday
Product updates
Burcon unveils canola protein isolate for egg replacement
Plant-based Dairy & Egg
Yesterday
Product updates
Bene Meat Technologies produces first cultivated burger at parity with premium beef
Cell-cultured Meat
Yesterday
Geographic expansion
Regulation/policy
The Better Meat Co. expands to Asia with Singapore approval for Rhiza mycoprotein
Plant-based Meat
Yesterday
Listing
Pony.ai files for US IPO
Auto Tech
Yesterday
Product updates
MineOS launches DSR management 2.0
Digital Privacy Tools
Yesterday
Product updates
LatticeFlow launches the first evaluation framework for EU AI Act compliance
Generative AI Infrastructure
Yesterday
Product updates
Cognitive3D launches custom dashboards for XR analytics
Extended Reality
Oct 16, 2024
Funding
Mindtech raises GBP 4.4 million in funding to develop AI vision technology
Extended Reality
Oct 16, 2024
Generative AI Infrastructure

Generative AI Infrastructure

Jan 8, 2024

Syntiant Corp. announces optimizations to run LLMs with high efficiency

Product updates

  • Syntiant Corp. announced optimizations that reduce the computational footprint of large language model (LLM) architectures.

  • Key features include a novel algorithm determining sparsity fraction for significant speed-ups, a 50% increase in output token generation speed on a benchmark, and improvements in interoperability and processing power.

  • Syntiant Corp. develops silicon and hardware-agnostic models that are deployed globally to power edge AI speech, audio, sensor, and vision applications across a wide range of industrial and consumer use cases.

  • Syntiant’s chip solutions merge deep learning with semiconductor design to produce ultra-low-power, high-performance, deep neural network processors. 

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.