NVIDIA B200的超级系统胜过上一代的系统，即代币生成每秒的3倍

加利福尼亚州圣何塞，2025年4月3日/美通社/ - Super Micro Computer，Inc。（SMCI），AI/ML，HPC，云，存储和5G/Edge的全部IT解决方案提供商

SAN JOSE, Calif., April 3, 2025 /PRNewswire/ -- Super Micro Computer, Inc. (NASDAQ: SMCI), a leading provider of advanced technology enterprise computing, storage, networking solutions, and a Total IT Solution Provider for Artificial Intelligence (AI) and Machine Learning (ML), today announced first-to-market industry leading performance on several MLPerf Inference v5.0 benchmarks, using the NVIDIA HGX B200 8-GPU. The 4U liquid-cooled and 10U air-cooled systems achieved the best performance in select benchmarks. Supermicro demonstrated more than 3 times the tokens per second (Token/s) generation for Llama2-70B and Llama3.1-405B benchmarks compared to H200 8-GPU systems.

加利福尼亚州圣何塞，2025年4月3日 / PRNewswire / -Super Micro Computer，Inc。（NASDAQ：SMCI），高级技术企业计算，存储，网络解决方案以及全部IT解决方案提供商人工智能（AI）和机器学习（ML）的全部IT解决方案提供商，今天宣布的第一台Bench beinder beander beanch verne venden 2. HGX B200 8-GPU。 4U液冷和10U气冷系统在精选基准中实现了最佳性能。与H200 8-GPU系统相比，SuperMicro的Llama2-70B和Llama3.1-405B基准的Llama2-70B和Llama3.1-405B基准的代币每秒（令牌/s）生成的3倍以上。

"Supermicro remains a leader in the AI industry, as evidenced by the first new benchmarks released by MLCommons in 2025," said Charles Liang, president and CEO, Supermicro. "Our building block architecture enables us to be first-to-market with a diverse range of systems optimized for various workloads. We continue to closely collaborate with NVIDIA to fine-tune our systems and secure a leadership position in AI workloads."

Supermicro总裁兼首席执行官Charles Liang说：“ Supermicro仍然是AI行业的领导者，这是MLCommons于2025年发布的首次新基准的证明。” “我们的构件架构使我们能够以针对各种工作量进行优化的各种系统进行首次上市。我们将继续与NVIDIA紧密合作，以微调我们的系统并确保AI工作负载中的领导地位。”

Learn more about the new MLPerf v5.0 Inference benchmarks at: https://mlcommons.org/benchmarks/inference-datacenter/

在以下网址了解有关新的MLPERF V5.0推理基准的更多信息：https：//mlcommons.org/benchmarks/inference-datacenter/

Supermicro is the only system vendor publishing record MLPerf inference performance (on select benchmarks) for both the air-cooled and liquid-cooled NVIDIA HGX B200 8-GPU systems. Both air-cooled and liquid-cooled systems were operational before the MLCommons benchmark start date. Supermicro engineers optimized the systems and software to showcase the impressive performance. Within the operating margin, the Supermicro air-cooled B200 system exhibited the same level of performance as the liquid-cooled B200 system. Supermicro has been delivering these systems to customers while we conducted the benchmarks.

SuperMicro是唯一针对气冷和液冷NVIDIA HGX B200 8-GPU系统的系统供应商发布记录MLPERF推理性能（在某些基准测试中）。在MLCommons基准开始日期之前，气冷和液冷系统都在运行。超级工程师优化了系统和软件，以展示令人印象深刻的性能。在操作余量中，超级气冷B200系统表现出与液冷B200系统相同的性能水平。在我们进行基准测试时，Supermicro一直向客户交付这些系统。

MLCommons emphasizes that all results be reproducible, that the products are available and that the results can be audited by other MLCommons members. Supermicro engineers optimized the systems and software, as allowed by the MLCommons rules.

MLCommons强调所有结果都是可重现的，产品可用，并且可以由其他MLCommons成员审核结果。超级工程师根据MLCommons规则允许优化系统和软件。

The SYS-421GE-NBRT-LCC (8x NVIDIA B200-SXM-180GB) and SYS-A21GE-NBRT (8x NVIDIA B200-SXM-180GB) showed performance leadership running the Mixtral 8x7B Inference, Mixture of Experts benchmarks with 129,000 tokens/second. The Supermicro air-cooled and liquid-cooled NVIDIA B200 based system delivered over 1,000 tokens/second inference for the large Llama3.1-405b model, whereas the previous generations of GPU systems have much smaller results. For smaller inferencing tasks, using the LLAMA2-70b benchmark, a Supermicro system with the NVIDIA B200 SXM-180GB installed shows the highest performance from a Tier 1 system supplier.

SYS-421GE-NBRT-LCC（8x NVIDIA B200-SXM-180GB）和SYS-A21GE-NBRT（8x NVIDIA B200-SXM-180GB）显示出性能领导力，运行MixTRAL 8x7b推理，专家混合物与129,000个代币/秒。基于Supermicro气冷和液冷NVIDIA B200的系统，用于大型Llama3.1-405b模型的1000多个令牌/秒推断，而GPU的前几代GPU系统的结果较小。对于较小的推断任务，使用Llama2-70B基准，这是一种具有NVIDIA B200 SXM-180GB的超级系统，已安装了Tier 1 System System供应商的最高性能。

Specifically:

具体来说：

* The Supermicro liquid-cooled system SYS-421GE-NBRT-LCC (8x NVIDIA B200-SXM-180GB) achieved the best performance in select benchmarks.

* Supermicro液体冷却系统SYS-421GE-NBRT-LCC（8x NVIDIA B200-SXM-180GB）在精选的基准测试中取得了最佳性能。

* The Supermicro air-cooled system SYS-A21GE-NBRT (8x NVIDIA B200-SXM-180GB) also achieved the best performance in select benchmarks.

* Supermicro气冷系统SYS-A21GE-NBRT（8x NVIDIA B200-SXM-180GB）在精选基准测试中也取得了最佳性能。

* Both systems achieved the best performance in the Mixtral 8x7B Inference, Mixture of Experts benchmarks with 129,000 tokens/second.

*这两个系统在混合8x7b推理中都达到了最佳性能，专家的混合物用129,000个令牌/秒进行了基准。

* The Supermicro air-cooled and liquid-cooled NVIDIA B200 based system delivered over 1,000 tokens/second inference for the large Llama3.1-405b model.

*基于SuperMicro气冷和液冷NVIDIA B200的系统，用于大型Llama3.1-405b型号的1,000个令牌/秒推断。

* For smaller inferencing tasks, using the LLAMA2-70b benchmark, a Supermicro system with the NVIDIA B200 SXM-180GB installed shows the highest performance from a Tier 1 system supplier.

*对于较小的推论任务，使用Llama2-70B基准，这是一种具有NVIDIA B200 SXM-180GB的超级系统，显示了Tier 1 System System供应商的最高性能。

"We at MLCommons are pleased to see results from members demonstrating significant performance gains compared to earlier generations of systems,” said David Kanter, Head of MLPerf at MLCommons. “Customers will be pleased by the performance improvements achieved which are validated by the neutral, representative and reproducible MLPerf results. We encourage members to continue pushing the boundaries of deep learning technology and we look forward to seeing the results of future generations of hardware and software.”

MLCommons的MLPERF负责人David Kanter说：“ MLCommons很高兴看到成员与早期系统相比表现出显着性能增长的结果。” “客户将对所取得的绩效改进感到满意，这些改进得到了中性，代表性和可重复的MLPERF结果的验证。我们鼓励成员继续推动深度学习技术的界限，我们期待看到后代的硬件和软件的结果。”

Supermicro offers a comprehensive AI portfolio with over 100 GPU-optimized systems, both air-cooled and liquid-cooled options, with a choice of CPUs, ranging from single-socket optimized systems to 8-way multiprocessor systems. Supermicro rack-scale systems include computing

SuperMicro提供了全面的AI投资组合，具有100多个GPU优化的系统，包括气冷和液体冷却选项，可选择CPU，范围从单插入优化的系统到8向多处理器系统。超级机架规模系统包括计算