Dell unveils Nvidia Vera CPU offerings, launches its first Groq 3 LPU rack-scale inference solution
Article excerpt
All have been purpose-built for agentic AI, Dell said Dell Technologies has expanded its Dell AI Factory with Nvidia product portfolio, adding a Vera CPU server and rack, and a rack-scale inference system built on Groq 3 Language Processing Units (LPUs), to its hardware lineup. In a statement, Dell said its AI Factory platform has surpassed 6,500 customers, up from 5,000 in the previous quarter. The Dell PowerEdge M9882 comprises 256 Nvidia Vera CPUs in a single 48U rack, allowing companies to maximize data center power and cooling capacity by separating out CPU compute from GPU clusters. Dell said the rack has been purpose-built to support agentic AI workloads, and offers orchestration, tool use, code execution and evaluation, which can run alongside GPU infrastructure for model inference. Meanwhile, the Dell PowerEdge R8822 server is an air-cooled, two-socket Nvidia Vera CPU offering that fits into standard 19-inch rack environments. Like its rack-scale counterpart, the R8822 has also been optimized for agentic AI workloads and can run reinforcement learning, data processing, and analytics, with support for up to four double-wide GPUs to accelerate AI and compute-intensive tasks. Finally, Dell has launched the PowerEdge XE9810, the first offering from the company to feature Groq 3 LPUs. Featuring 16 direct-liquid-cooled compute trays, Dell did not provide details on the...
Keep reading with a free account
The rest of this article, and every signal for Dell, is in your free account.
Extracted from this sentence
The Dell PowerEdge R8822 will be available this month, with the M9882 and XE9810 coming in Q1 2027.
