Cerebras CS-3 vs. Nvidia B200: 2024 AI Accelerators Compared
In the fast-paced world of AI hardware, the Cerebras CS-3…
Cerebras CS-3: the world’s fastest and most scalable AI accelerator
Today Cerebras is introducing the CS-3, our…
Sparsity Made Easy – Introducing the Cerebras PyTorch Sparsity Library
We release our PyTorch-based sparsity library allowing ML…
Introducing gigaGPT: GPT-3 sized models in 565 lines of code
GigaGPT is Cerebras’ implementation of Andrei Karpathy’s…
Cerebras Pioneers Ethical AI Development through Collaborative AI Initiatives
Today, Cerebras proudly revealed our pivotal role as a…
Cerebras Software Release 2.0: 50% Faster Training, PyTorch 2.0 Support, Diffusion Transformers, and More
Today we are excited to announce Cerebras software release…
How we fine-tuned Llama2-70B to pass the US Medical License Exam in a week
New open-access model by M42 outperforms GPT-3.5 in…
BTLM-3B-8K: 7B Performance in a 3 Billion Parameter Model
Cerebras and Opentensor introduce a new standard for…
Introducing Condor Galaxy 1: a 4 exaFLOPS Supercomputer for Generative AI
Cerebras, in partnership with G42 unveils CG-1, a 4…
SlimPajama: A 627B token, cleaned and deduplicated version of RedPajama
Today we are releasing SlimPajama – the largest…
Cerebras Architecture Deep Dive: First Look Inside the HW/SW Co-Design for Deep Learning [Updated]
Our ML-optimized architecture enables the largest models to…
Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models
Cerebras open sources seven GPT-3 models from 111 million…
Harnessing the Power of Sparsity for Large GPT AI Models
Enabling innovation of novel sparse ML techniques to…
Context is Everything: Why Maximum Sequence Length Matters
GPU-Impossible™ sequence lengths on Cerebras systems may…
