SparseGPT – Sparsifying LLMs for efficient inference – https://
hubs.li/Q01Z9ysx0
@cerebras
-
SparseGPT: Sparsifying LLMs for efficient inference
By
–
-
Sparse models match dense accuracy with fewer flops
By
–
SPDF – Matching the downstream accuracy of a dense model with a sparse model using fewer flops – https://
hubs.li/Q01Z9v0G0 -
Cerebras and G42 Partner for Advanced AI Supercomputing Solutions
By
–
Together, Cerebras and G42’s partnership delivers blazing-fast AI supercomputing, deep AI expertise, and access to unique domain-specific data sets. Groundbreaking results soon to follow. Learn how we can help with your generative AI projects – https://
hubs.li/Q01YxdBl0 -
Cerebras Condor Galaxy Named World’s Fastest AI Training Supercomputer
By
–
WIRED reports "The world now has a new fastest AI training supercomputer. Condor Galaxy, a network of 9 interconnected AI supercomputers, was brought to life by the US-based AI company Cerebras Systems together with G42, UAE-based technology holding group https://
hubs.li/Q01YwfJP0 -
CG-1 Simplifies Massive GPU Cluster Distribution for AI Models
By
–
“Many cloud companies have announced massive GPU clusters that cost billions of dollars to build and are extremely difficult to use. Distributing a single model over 1000s of tiny GPUs takes months of time from dozens of people with rare expertise. CG-1 eliminates this challenge"
-
Condor Galaxy 1: Cerebras G42 Partnership Dramatically Reduces AI Training
By
–
“Condor Galaxy 1 (CG-1), the result of the Cerebras and G42 partnership, dramatically reduces AI training time while eliminating the pain of distributed compute,” says our CEO, Andrew Feldman. pic.twitter.com/CEkomoyaMB
— Cerebras (@cerebras) 21 juillet 2023“Condor Galaxy 1 (CG-1), the result of the Cerebras and G42 partnership, dramatically reduces AI training time while eliminating the pain of distributed compute,” says our CEO, Andrew Feldman.
-
Cerebras Introduces Condor Galaxy-1 Exaflop Supercomputer
By
–
To learn more about CG-1, read our detailed technical blog. https://
cerebras.net/blog/introduci
ng-condor-galaxy-1-a-4-exaflop-supercomputer-for-generative-ai/
… -
Cerebras Launches Condor Galaxy 1 AI Hardware System
By
–
Condor Galaxy 1 is up and running at the Colovore data center in Santa Clara, CA. We will be unveiling an exciting new model trained on CG-1 at ICML 2023. Follow us on Twitter and sign up to our newsletter to stay up to date! https://
info.cerebras.net/subscribe -
Cerebras: 20x Memory Advantage Enables 100B Models Natively
By
–
Because our compute and memory are ~20x larger, even 100B models fit entirely in memory without tensor/pipeline parallel gymnastics. Our GPT implementation uses 1/20th the lines of code of Nvidia Megatron. Huge models work out of the box on Cerebras. This is why G42 picked us.
-
Cerebras Cloud Democratizes AI Supercomputing Access Globally
By
–
CG-1 will be served through the Cerebras Cloud to both G42 and external customers. Big picture – Cerebras is now providing AI supercomputing instances – the same kind that Azure provided OpenAI. Our goal is to democratize AI access so all teams can build large scale AI models.