联想H100 GPU服务器

ThinkSystem NVIDIA H100 PCIe Gen5 GPUs

Product Guide

The ThinkSystem NVIDIA H100 GPU delivers unprecedented performance, scalability, and security for every

workload. The GPUs use breakthrough innovations in the NVIDIA Hopper™ architecture to deliver industry-

leading conversational AI, speeding up large language models by 30X over the previous generation.

The NVIDIA H100 GPU features fourth-generation Tensor Cores and the Transformer Engine with FP8

precision, further extending NVIDIA’s market-leading AI leadership with up to 9X faster training and an

incredible 30X inference speedup on large language models. For high-performance computing (HPC)

The NVIDIA H100 family is available in both double-wide PCIe adapter form factor and in SXM form factor.

The latter is used in Lenovo's Neptune direct-water-cooled ThinkSystem SD665-N V3 server for the ultimate

in GPU performance and heat management.

The NVIDIA H100 NVL Tensor Core GPU is optimized for Large Language Model (LLM) Inferences, with its

high compute density, high memory bandwidth, high energy efficiency, and unique NVLink architecture.

Click here to check for updates

Part number information

The following table shows the part numbers for the ThinkSystem NVIDIA H100 GPU.

The PCIe option part numbers includes the following:

One GPU with full-height (3U) adapter bracket attached

Documentation

The GPU uses breakthrough innovations in the NVIDIA Hopper™ architecture to deliver industry-leading

conversational AI, speeding up large language models (LLMs) by 30X over the previous generation.

The PCIe versions of the NVIDIA H100 GPUs include a five-year software subscription, with enterprise

support, to the NVIDIA AI Enterprise software suite, simplifying AI adoption with the highest performance.

This ensures organizations have access to the AI frameworks and tools they need to build accelerated AI

workflows such as AI chatbots, recommendation engines, vision AI, and more.

The NVIDIA H100 GPU features fourth-generation Tensor Cores and the Transformer Engine with FP8

precision, further extending NVIDIA’s market-leading AI leadership with up to 9X faster training and an

incredible 30X inference speedup on large language models. For high-performance computing (HPC)

applications, the GPU triples the floating-point operations per second (FLOPS) of FP64 and adds dynamic

accelerated compute needs, H100 is the world’s most advanced chip ever built. It features major

advances to accelerate AI, HPC, memory bandwidth, interconnect, and communication at data center

scale.

Transformer Engine

The Transformer Engine uses software and Hopper Tensor Core technology designed to accelerate

training for models built from the world’s most important AI model building block, the transformer.

Hopper Tensor Cores can apply mixed FP8 and FP16 precisions to dramatically accelerate AI

calculations for transformers.

NVLink Switch System

The NVLink Switch System enables the scaling of multi-GPU input/output (IO) across multiple

H100 GPUs.

Second-Generation Multi-Instance GPU (MIG)

The Hopper architecture’s second-generation MIG supports multi-tenant, multi-user configurations in

virtualized environments, securely partitioning the GPU into isolated, right-size instances to maximize

quality of service (QoS) for 7X more secured tenants.

DPX Instructions

Hopper’s DPX instructions accelerate dynamic programming algorithms by 40X compared to CPUs

and 7X compared to NVIDIA Ampere architecture GPUs. This leads to dramatically faster times in

disease diagnosis, real-time routing optimizations, and graph analytics.

The following figure shows the NVIDIA H100 SXM5 4-GPU Board installed in the ThinkSystem SD665-N V3

* With structural sparsity enabled