AMD and Cerebras Join Forces to Develop Ultra-Low Latency AI Inference Platform
AMD has partnered with Cerebras Systems to build a computing platform that combines AMD Instinct accelerators with Cerebras' SRAM-based chips to achieve ultra-low latency inference for AI agents. The joint solution aims to fill a gap in AMD's portfolio after Nvidia acquired Groq for $20 billion in December.
Cerebras Systems
NVIDIA
