20X performance and 1/5th the price of GPUs- available today Developers can now leverage the power of wafer-scale compute for AI inference via a simple API SUNNYVALE, Calif. – Today, Cerebras Systems, the pioneer in high performance AI compute, announced Cerebras Inference, the fastest AI inference solution in the world. Delivering 1,800 tokens per second for Llama 3.1 8B and 450 tokens per second for Llama 3.1 … Continue reading Cerebras Launches the World’s Fastest AI Inference

Glenda Dorchak and Paul Auvil join Cerebras’ Board of Directors Bob Komin named CFO SUNNYVALE, Calif. – Cerebras Systems, a pioneer in accelerating generative AI, today announced the appointment of new independent Board members Glenda Dorchak, a former IBM, Intel and Spansion executive, and Paul Auvil, former CFO of VMWare and Proofpoint. Both industry veterans bring a range of corporate governance and technology expertise to … Continue reading Cerebras Announces New Board Members and Chief Financial Officer