Does your organization require optimized infrastructure for deploying AI/ML trained models at the edge? The Qualcomm Cloud AI 100 Accelerator for HPE dramatically improves server performance on AI/ML inference workloads for faster insights and higher accuracy data transformations on computer vision, natural language, and other state-of-the-industry AI/ML use cases. Based on the Qualcomm AI Core, this server accelerator is tailored for inference, supporting model customization and quantization to lower precision datatypes for optimized performance and industry-leading power efficiency. With low power consumption, the Qualcomm Cloud AI 100 Accelerator for HPE can increase performance while lowering operating cost.
SKU # R9Q09A
Existing selections will be lost. Click OK to proceed further.
Purpose-designed for AI/ML workloads, the Qualcomm Cloud AI 100 Accelerator for HPE is a market leader in performance and power efficiency based on industry-standard benchmarks including MLPerf.
Up to eight of these low-profile PCIe accelerators can be configured within an HPE Edgeline EL8000.
Each standard card delivers 350 TOPS while consuming only 75 watts of power.
Using ResNet-50 benchmark, performance translates to inferencing up to over 100,000 images per second in a single HPE Edgeline EL8000 system.
Each Qualcomm Cloud AI 100 Accelerator for HPE is rated at 75 Watts TDP.
Qualcomm Cloud AI 100 Accelerator for HPE design is a PCIe Gen4 (x8) connector in a low-profile form factor (both half-height and half-length) for compact use at the edge.
The Qualcomm Cloud AI 100 Accelerator for HPE leverages Qualcomm's 6th generation of AI/ML technologies and includes a comprehensive SDK and extensive suite of developer tools (compiler, performance optimization, and quantization tools) and code samples.
Features simplified support for popular AI/ML frameworks.
* Prices may vary based on local reseller.
