AMD and Cerebras partner on disaggregated AI inference solution

AMD (NASDAQ: AMD) and Cerebras Systems (NASDAQ: CBRS) announced a technical partnership to combine AMD Helios rackscale solutions with the Cerebras Wafer-Scale Engine in a single disaggregated AI inference workflow, the companies said in a press release issued July 23, 2026.

The joint solution is designed to handle two stages of AI inference independently: AMD Helios processes prompts and large context windows at high throughput, while the Cerebras Wafer-Scale Engine handles token generation at low latency. According to modeling conducted by AMD Performance Labs and Cerebras in July 2026, the combined system is expected to deliver up to 5x higher tokens per second per watt compared to a Cerebras Wafer-Scale Engine-only configuration, using the Kimi 2.6 1T model as a benchmark.

Cerebras plans to deploy AMD Helios systems in its data centers. The joint solution is expected to become available first through Cerebras Cloud in the second half of 2026.

The announcement was made at the Advancing AI 2026 event in San Francisco.

"AMD Helios delivers leadership performance and scale for the broadest range of inference workloads. Together with Cerebras, we are extending that leadership into the most latency-sensitive applications and creating a powerful new platform for real-time agentic AI," said Dr. Lisa Su, chair and CEO of AMD.

"Partnering with AMD gives us an incredible opportunity to bring that performance to even more customers," said Andrew Feldman, CEO and co-founder of Cerebras.

You May Also Be Interested In

• Honeywell Aerospace completes exchange of $16B in unregistered notes
• Rio Tinto secures power deal for Tomago Aluminium smelter to 2038
• Jefferies Upgrades Inovio Pharmaceuticals (INO) to Buy