Cerebras
Tag111 stories
A hardware company building wafer scale processors and a hosted inference service for large models. Readers can learn about the wafer scale engine design, inference throughput claims and benchmarks, how the chips compare with GPU clusters, funding and customers, and developer access to the API.
Cerebras breaks ground on Condor Galaxy 3, an AI supercomputer that can hit 8 exaFLOPsCerebras Unveils Its Next Waferscale AI Chip2023 was a great year for open-source LLMsMeet GigaGPT: Cerebras’ Implementation of Andrei Karpathy’s nanoGPT that Trains GPT-3 Sized AI Models in Just 565 Lines of CodeIntroducing gigaGPT: GPT-3 sized models in 565 lines of codeCerebras and Core42 start phase 2 for world’s largest AI supercomputersCore42 and Cerebras Sets New Benchmark for Arabic Large Language Models with the Release of Jais 30BFree GPUs and AI Chips Are Available to Run AINvidia just made a killing on AI – where is everyone else?Need for Speed: Cloud Power Moves Expand AI Supercomputing