NVIDIA L40S

Unparalleled AI and graphics performance for the data center.

NVIDIA L40S Datasheet
NVIDIA L40S Product Brief

The Most Powerful Universal GPU

Experience breakthrough multi-workload performance with the NVIDIA L40S GPU. Combining powerful AI compute with best-in-class graphics and media acceleration, the L40S GPU is built to power the next generation of data center workloads—from generative AI and large language model (LLM) inference and training to 3D graphics, rendering, and video.

Highlights

Universal Performance

Tensor Performance

 

1,466 TFLOPS¹

RT Core Performance

 

212 TFLOPS

Single-Precision Performance

 

91.6 TFLOPS

1 Peak rates are based on GPU boost clock.

Features

Powered by the NVIDIA Ada Lovelace Architecture

Fourth-Generation Tensor Cores

Hardware support for structural sparsity and optimized TF32 format provides out of-the-box performance gains for faster AI and data science model training. Accelerate AI-enhanced graphics capabilities with DLSS to upscale resolution with better performance in select applications.

Third-Generation RT Cores

Enhanced throughput and concurrent ray-tracing and shading capabilities improve ray-tracing performance, accelerating renders for product design and architecture, engineering, and construction workflows. See lifelike designs in action with hardware-accelerated motion blur and stunning real-time animations.

CUDA Cores

Accelerated single-precision floating point (FP32) throughput and improved power efficiency significantly boost performance for workflows like 3D model development and computer-aided engineering (CAE) simulation. Use enhanced 16-bit math capabilities (BF16) for mixed-precision workloads.

Transformer Engine

Transformer Engine dramatically accelerates AI performance and improves memory utilization for both training and inference. Harnessing the power of the Ada Lovelace fourth-generation Tensor Cores, Transformer Engine intelligently scans the layers of transformer architecture neural networks and automatically recasts between FP8 and FP16 precisions to deliver faster AI performance and accelerate training and inference.

Efficiency and Security

L40S GPU is optimized for 24/7 enterprise data center operations and designed, built, tested, and supported by NVIDIA to ensure maximum performance, durability, and uptime. The L40S GPU meets the latest data center standards, are Network Equipment-Building System (NEBS) Level 3 ready, and features secure boot with root of trust technology, providing an additional layer of security for data centers.

DLSS 3

L40S GPU enables ultra-fast rendering and smoother frame rates with NVIDIA DLSS 3. This breakthrough frame-generation technology leverages deep learning and the latest hardware innovations within the Ada Lovelace architecture and the L40S GPU, including fourth-generation Tensor Cores and an Optical Flow Accelerator, to boost rendering performance, deliver higher frames per second (FPS), and significantly improve latency.

Workloads

Multi-Workload Acceleration

Generative AI

Develop new services, insights, and original content. With next-generation AI, graphics, and media acceleration capabilities, the L40S delivers up to 5X higher inference performance than the previous-generation NVIDIA A40. ‌With breakthrough performance and 48 gigabytes (GB) of memory capacity, the L40S is the ideal platform for accelerating multimodal generative AI workloads.

Rendering and 3D Graphics

Power high-fidelity creative workflows with NVIDIA RTX™ graphics. With third-generation RT Cores that deliver up to 2X the real-time ray-tracing performance of the previous generation to power the creation of stunning visual content and high-fidelity creative workflows, from interactive rendering to real-time virtual production.

NVIDIA OVX L40S

Scalable Data Center Infrastructure for High-Performance AI and Graphics. Combined with NVIDIA Spectrum-X Ethernet technology and NVIDIA AI Enterprise software, NVIDIA OVX L40S delivers industry-leading performance to accelerate enterprise transformation with generative AI.

LLM Training and Inference

Accelerate AI training and inference workloads. Fourth-generation Tensor Cores with support for FP8 deliver exceptional AI computing performance to accelerate training and inference of state-of-the-art LLM and generative AI models.

NVIDIA Omniverse

Create and operate metaverse applications. NVIDIA Omniverse™ makes it possible to connect, develop, and operate the next wave of industrial digitalization applications. With powerful RTX graphics and AI capabilities, L40S delivers exceptional performance for Universal Scene Description (OpenUSD)-based 3D and simulation workflows built on Omniverse.

Performance

Breakthrough Performance

Image Generative AI

Stable Diffusion (images per minute) Measured performance; NVIDIA L40S Stable Diffusion v2.1, TRT 8.6.1, BS:1, FP16 | Stable Diffusion XL 1.0, TRT 8.6.1, BS:1, FP16

Large Language Model (LLM) Inference

1st Token Latency (ms) Measured performance; NVIDIA L40S Llama 2-7B/13B/70B, ISL=2048, OSL=128, BS=1;: FP8.

Specifications

NVIDIA L40S GPU

 
FP3291.6 teraFLOPS
TF32 Tensor Core366 teraFLOPS*
FP16733 teraFLOPS*
FP81,466 teraFLOPS*
RT Core Performance212 teraFLOPS
Max Power Consumption350W

*With Sparsity

NVIDIA L40S Datasheet
NVIDIA L40S Product Brief