OpenAI and Cerebras Join Forces to Revolutionize AI Compute

In a move that promises to revolutionise the field of artificial intelligence, OpenAI has announced a strategic partnership with Cerebras, a leading developer of purpose-built AI systems. The collaboration aims to integrate 750MW of ultra-low-latency AI compute into OpenAI's platform, enabling faster and more responsive AI models.

Cerebras' unique approach to accelerating long outputs from AI models involves putting massive compute, memory, and bandwidth together on a single giant chip, eliminating the bottlenecks that slow inference on conventional hardware. By integrating this technology into OpenAI's mix of compute solutions, users can expect faster responses, more natural interactions, and a stronger foundation for scaling real-time AI to even more people.

The partnership is all about making AI respond much faster, according to Sachin Katti of OpenAI. "When you ask a hard question, generate code, create an image, or run an AI agent, there's a loop happening behind the scenes: you send a request, the model thinks, and it sends something back," he explained. "When AI responds in real-time, users do more with it, stay longer, and run higher-value workloads."

The integration of Cerebras' low-latency capacity into OpenAI's inference stack will be phased across various workloads, expanding the platform's capabilities to support a wider range of applications. The partnership is expected to come online in multiple tranches through 2028.

Andrew Feldman, co-founder and CEO of Cerebras, expressed his excitement about the collaboration, stating that it brings together "the world's leading AI models with the world's fastest AI processor." He added that just as broadband transformed the internet, real-time inference will transform AI, enabling entirely new ways to build and interact with AI models.

The implications of this partnership are significant, promising to accelerate the development of real-time artificial intelligence. As OpenAI continues to push the boundaries of what is possible with AI, its collaboration with Cerebras marks a major milestone in the journey towards more powerful and responsive AI systems.