Gimlet Cloud will combine Cerebras’ wafer-scale systems with GPUs to accelerate AI inference, with the first Cerebras-powered data center expected to go online later this year.
- Cerebras and Gimlet target inference speeds of up to 3,000 tokens per second.
- Gimlet Cloud will combine Cerebras’ Wafer Scale Engine with GPUs.
- Gimlet is a launch partner for Cerebras’ latest CS-4 technology.
Cerebras Systems Inc. (CBRS) is teaming up with the applied AI research and infrastructure startup Gimlet Labs to bring its wafer-scale AI systems into Gimlet Cloud.
With this collaboration, the companies are targeting inference speeds of up to 3,000 tokens per second for agentic and real-time AI applications. The first Cerebras-powered Gimlet Cloud data center is expected to come online later this year.
The collaboration will span infrastructure through developer application programming interfaces (APIs), as they work to make faster AI inference available at production scale.
How The System Works
Inference is the process through which a trained AI model produces responses or other outputs. For applications such as AI agents, voice and video systems, and assistants, how quickly those outputs are generated can directly affect how responsive the application feels.
Gimlet Cloud will combine Cerebras’ Wafer Scale Engine with graphics processing units (GPUs) rather than relying on one type of processor for every part of the workload.
Gimlet’s technology divides AI inference into distinct phases and directs each phase to the computing hardware best suited to perform it. This approach combines Cerebras’ fast token generation with the high throughput offered by GPUs.
The companies plan to deliver up to 3,000 tokens per second at production scale, said Gimlet CEO Zain Asgar.
Gimlet Becomes CS-4 Launch Partner
Gimlet will also serve as a launch partner for Cerebras’ CS-4 technology, providing Gimlet Cloud customers with access to Cerebras’ latest systems.
Cerebras Chief Technology Officer Sean Lie said making Cerebras a native part of Gimlet’s inference cloud would bring its AI inference technology to more developers at production scale.
Cerebras and Gimlet have worked together on customer engagements since last year, and an integrated system is already serving tokens in private deployments.
The companies now plan to expand the collaboration across software, infrastructure design, APIs, developer tools, optimization, validation, and production operations.
Retail Sentiment Around CBRS Stock
On Stocktwits, retail investor sentiment around CBRS stock remained in the ‘bearish’ territory.
So far this year, CBRS stock price has fallen more than 36%. In comparison, the ARK Innovation ETF (ARKK) and the State Street SPDR S&P Semiconductor ETF (XSD), which hold the stock, have risen around 15% and 58%, respectively, over the same period.
See Also: MDB Stock Plunges After CEO Leaves For Meta – Analysts Weigh Enterprise Ties Against Ittycheria Return
For updates and corrections, email newsroom[at]stocktwits[dot]com.<
