HPE ProLiant Compute servers - Dominate AI inference benchmarks - Again!
Experience unprecedented computational performance with HPE ProLiant DL380a Gen12. Ideal for AI workloads, this server is transforming the way AI computations are performed. The ProLiant series has dominated AI inference benchmarks with eight #1 rankings across MLPerf benchmarks. In addition to benchmark dominance, the HPE ProLiant DL380a Gen12 delivers outstanding performance per GPU on MLPerf™ Datacenter v5.1, achieving amazing results in terms of queries per second. The server also came out as a champion in both DLRM and Llama benchmarks again! According to the MLPerf Datacenter v5.1 results, HPE was the first and only supplier to submit results with such remarkable performance levels. The HPE ProLiant DL380a Gen12 powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, showcases our commitment to providing powerful, optimized, and secure solutions for tackling AI and ML workloads. Learn more about how wecan help you harness the computational power of HPE ProLiant DL380a Gen12 for your AI workloads.
What are the benchmark achievements of HPE ProLiant Compute servers?
HPE ProLiant Compute servers have achieved notable rankings in AI inference benchmarks, securing eight #1 positions across MLPerf benchmarks. The HPE ProLiant DL385 Gen11 leads with 3,962.78 samples per second per GPU, while the DL380a Gen12 demonstrates outstanding performance with 65,021 queries per second per GPU in the MLPerf Datacenter v5.0.
How does the HPE ProLiant DL380a Gen12 perform in specific benchmarks?
The HPE ProLiant DL380a Gen12 has shown impressive results in benchmark tests, achieving 41,357 queries per second per GPU in the DLRM-v2-99 benchmark and outperforming competitors in the Llama2-70b-99 and Llama2-70b-99.9 benchmarks with significant performance metrics.
What unique features does the HPE ProLiant DL384 Gen12 offer?
The HPE ProLiant DL384 Gen12 is notable for being the only server utilizing the NVIDIA GH200 NVL2 accelerator, achieving 161,030 queries per second and 174,456 samples per second in benchmark tests. This unique capability enhances its performance in AI inference tasks.
HPE ProLiant Compute servers - Dominate AI inference benchmarks - Again!
published by Jonathan's Technology Solutions
Since 1980, Jonathan's has been helping businesses in the Tri-State area save money and build long-term operational IT efficiency.
We deliver customized, multi-branded business technology solutions with best-in-class business-grade equipment and personalized care. Nationally, we were among the first dozen Apple authorized dealers, which shows our age and adaptability. We now have contracts with all leading distributors to ensure our clients have the best. We have always been and will always be agile, ethical, and responsive to our clients' ever-changing needs.
The white-glove service we deliver primarily in hospital and healthcare settings alike, the most stringent environments, is the standard care we offer to all clients across different industries.
If you are curious about the value and ROI we promise or would like a free consultation to discuss any potential IT concerns, please visit us at jonathans.com, where you may utilize our chatbot to speak with our team, leave a form, or call in. We look forward to hearing from you!
Sign in with LinkedIn