Cerebras Systems Sets Record for Largest AI Models Ever Trained on A Single Device

Single CS-2 System trains multi-billion parameter NLP models including GPT-3L 1.3 Billion, GPT-J 6 Billion , GPT-3 13…


0 Comments7 Minutes

Leading Supercomputer Sites Choose Cerebras For AI Acceleration

Across the United States and Europe, supercomputing centers depend on wafer-scale solutions from Cerebras for high…


0 Comments7 Minutes

NCSA Deploys Cerebras CS-2 in New HOLL-I Supercomputer for Large-Scale Artificial Intelligence

NCSA unveils new system, HOLL-I, equipped with Cerebras CS-2 for public and industrial artificial intelligence research…


0 Comments5 Minutes

HPE, Cerebras build AI supercomputer for scientific research

Wafer madness hits the LRZ in HPE Superdome supercomputer wrapper


0 Comments1 Minute

Leibniz Supercomputing Centre Accelerates AI Innovation in Bavaria with Next-Generation AI System from Cerebras Systems and Hewlett Packard Enterprise

Leibniz Supercomputing Centre’s new advanced AI system will enable researchers to accelerate initiatives around machine…


0 Comments11 Minutes

Cerebras @ AI Field Day 2022

Accelerating AI and HPC with Wafer-Scale Compute from Cerebras Systems


0 Comments1 Minute

Getting Started with PyTorch BERT Models on the Cerebras CS-2 System

This walk through shows how easy it is to adapt and run PyTorch models on a Cerebras system using the many convenient…


0 Comments16 Minutes

TotalEnergies and Cerebras Create Massively Scalable Stencil Algorithm

TotalEnergies used the Cerebras CS-2 system to turn a problem long accepted to be memory-bound into compute-bound. On a…


0 Comments8 Minutes

Cerebras Systems Expands PyTorch Support, Delivers Capability for Giant Model Training

Expanded Software Platform Enables Developers to Seamlessly Scale Large Language Models


0 Comments5 Minutes

Cerebras Software Platform R1.2 is Out!

Our new release expands PyTorch support and unlocks Cerebras' weight streaming technology for extreme-scale models.


0 Comments6 Minutes

When Time is Money: Accelerating NLP Model Training at a Leading Financial Institution

Our CS-2 system delivered the compute performance of more than 120 AI-optimized GPUs, making it possible to train large…


0 Comments4 Minutes

nference Accelerates Self-Supervised Language Model Training with Cerebras CS-2 System

The ability to harness vast amounts of health data using advanced AI technology will lead to new discoveries and…


0 Comments5 Minutes

TotalEnergies and Cerebras: Accelerating into a Multi-Energy Future (Updated)

Cerebras is helping TotalEnergies to advance their clean energy roadmap by delivering >200X speedup on a finite…


0 Comments10 Minutes

If You’re Doing Pharma and Life Sciences AI Research Without a Cerebras System, You’re Doing it Wrong

Cerebras AI accelerator systems make it possible to train complex models using huge datasets at the speed of science.


0 Comments7 Minutes

Cerebras Systems and G42 to Partner to Bring High-Performance AI Compute to the Middle East

Expanded Software Platform Enables Developers to Seamlessly Scale Large Language Models


0 Comments4 Minutes

Cerebras Systems Introduces Software Development Kit to Extend Breadth of Wafer-Scale Applications

Expanded Software Platform Enables Developers to Seamlessly Scale Large Language Models


0 Comments4 Minutes

Cerebras – Eye On AI

Eye On A.I.


0 Comments1 Minute

Cirrascale Cloud Services® and Cerebras Systems Announce Availability of Cerebras Cloud @ Cirrascale for Unparalleled Artificial Intelligence Performance

New Partnership Democratizes AI by Delivering Highest Performing AI Compute and Massively Scalable Deep Learning in an…


0 Comments5 Minutes

Scaling Up and Out: Training Massive Models on Cerebras Systems using Weight Streaming

A look at how the Wafer-Scale Engine trains models much larger than even itself - approaching the scale of a human…


0 Comments22 Minutes

Cerebras Systems Announces World’s First Brain-Scale Artificial Intelligence Solution

New Partnership Democratizes AI by Delivering Highest Performing AI Compute and Massively Scalable Deep Learning in an…


0 Comments16 Minutes

Error Compensation Mechanism in Online Normalization

Online Normalization is a new technique for normalizing the hidden activations of a neural network.


0 Comments7 Minutes