"With the introduction of the new AMD 'Helios' and our purpose-built HPE scale-up networking solution, we are providing our cloud service provider customers with faster deployments, greater flexibility, and reduced risk in how they scale AI computing in their businesses,"
"leverages HPE's AI-native automation and assurance capabilities to simplify network operations for faster deployment and overall cost savings"
"Broadcom is proud to take part in this collaboration to advance open, Ethernet -based AI infrastructure for scale-up."
HPE has introduced an AMD Helios offering that provides a turnkey infrastructure option engineered for trillion-parameter AI training and large-scale inference. The solution integrates Juniper Networks technology and a purpose-built scale-up switch and software co-developed with Broadcom, optimized for Helios architecture and delivering improved AI workload performance over standard Ethernet. The offering includes Broadcom Tomahawk 6, 72 AMD Instinct MI455X GPUs per rack, AMD Pensando networking, and AMD ROCm software. The solution incorporates AI-native automation and assurance to simplify network operations, aiming to speed deployments, increase flexibility, and reduce scaling risk for cloud service providers.
Read at IT Pro
Unable to calculate read time
Collection
[
|
...
]