Cerebras Products Customers Partners Developers Resources Pricing Company Contact us Get Started Mar 13 2026 AWS and Cerebras Collaboration Aims to Set a New Standard for AI Inference Speed and Performance in the Cloud Deployed in AWS data centres and accessed through Amazon Bedrock, AWS Trainium +, the company said on 13 March 2026.
AWS and Cerebras Collaboration Aims to Set a New Standard for AI Inference Speed and Performance in the Cloud, the company said on 13 March 2026. Industry-leading speed and performance: With AWS Trainium optimised for prefill and Cerebras CS-3 optimised for decode, this innovative integrated system will provide unmatched performance and speed for AI inference. Pioneering cloud collaboration: AWS is the first cloud provider for Cerebras's disaggregated inference solution, available soon through Amazon Bedrock.
Seattle and Sunnyvale, CA – March 13, 2026 – Amazon Web Services, Inc. (AWS), an Amazon.com, Inc. company (NASDAQ: AMZN), and Cerebras Systems today announced a collaboration that will deliver the fastest AI inference solutions available for generative AI applications and LLM workloads in the coming months. The solution, to be deployed on Amazon Bedrock in AWS data centres, combines AWS Trainium-powered servers, Cerebras CS-3 systems, and Elastic Fabric Adapter (EFA) networking.
For enterprise buyers, the useful next step is to map the claim to controls, data residency and measurable outcomes—and to ask for evidence on failure modes, oversight and auditability before treating the release as production-ready fact.