Inference Performance

Dec 05, 2024

Spotlight: Perplexity AI Serves 400 Million Search Queries a Month Using NVIDIA Inference Stack

The demand for AI-enabled services continues to grow rapidly, placing increasing pressure on IT and infrastructure teams. These teams are tasked with...

7 MIN READ

Image of the TensorRT-LLM icon next to multiple other icons of computer activities.

Dec 02, 2024

TensorRT-LLM Speculative Decoding Boosts Inference Throughput by up to 3.6x

NVIDIA TensorRT-LLM support for speculative decoding now provides over 3x the speedup in total token throughput. TensorRT-LLM is an open-source library that...

9 MIN READ

Nov 21, 2024

NVIDIA TensorRT-LLM Multiblock Attention Boosts Throughput by More Than 3x for Long Sequence Lengths on NVIDIA HGX H200

Generative AI models are advancing rapidly. Every generation of models comes with a larger number of parameters and longer context windows. The Llama 2 series...

5 MIN READ

Nov 19, 2024

Llama 3.2 Full-Stack Optimizations Unlock High Performance on NVIDIA GPUs

Meta recently released its Llama 3.2 series of vision language models (VLMs), which come in 11B parameter and 90B parameter variants. These models are...

6 MIN READ

Nov 15, 2024

Streamlining AI Inference Performance and Deployment with NVIDIA TensorRT-LLM Chunked Prefill

In this blog post, we take a closer look at chunked prefill, a feature of NVIDIA TensorRT-LLM that increases GPU utilization and simplifies the deployment...

4 MIN READ

Nov 08, 2024

5x Faster Time to First Token with NVIDIA TensorRT-LLM KV Cache Early Reuse

In our previous blog post, we demonstrated how reusing the key-value (KV) cache by offloading it to CPU memory can accelerate time to first token (TTFT) by up...

5 MIN READ

Nov 01, 2024

3x Faster AllReduce with NVSwitch and TensorRT-LLM MultiShot

Deploying generative AI workloads in production environments where user numbers can fluctuate from hundreds to hundreds of thousands – and where input...

5 MIN READ

Oct 28, 2024

NVIDIA GH200 Superchip Accelerates Inference by 2x in Multiturn Interactions with Llama Models

Deploying large language models (LLMs) in production environments often requires making hard trade-offs between enhancing user interactivity and increasing...

7 MIN READ

Oct 09, 2024

NVIDIA Grace CPU Delivers World-Class Data Center Performance and Breakthrough Energy Efficiency

NVIDIA designed the NVIDIA Grace CPU to be a new kind of high-performance, data center CPU—one built to deliver breakthrough energy efficiency and optimized...

8 MIN READ

Oct 09, 2024

Boosting Llama 3.1 405B Throughput by Another 1.5x on NVIDIA H200 Tensor Core GPUs and NVLink Switch

The continued growth of LLMs capability, fueled by increasing parameter counts and support for longer contexts, has led to their usage in a wide variety of...

8 MIN READ

Sep 26, 2024

Low Latency Inference Chapter 2: Blackwell is Coming. NVIDIA GH200 NVL32 with NVLink Switch Gives Signs of Big Leap in Time to First Token Performance

Many of the most exciting applications of large language models (LLMs), such as interactive speech bots, coding co-pilots, and search, need to begin responding...

8 MIN READ

Sep 24, 2024

NVIDIA GH200 Grace Hopper Superchip Delivers Outstanding Performance in MLPerf Inference v4.1

In the latest round of MLPerf Inference – a suite of standardized, peer-reviewed inference benchmarks – the NVIDIA platform delivered outstanding...

7 MIN READ

Sep 05, 2024

Low Latency Inference Chapter 1: Up to 1.9x Higher Llama 3.1 Performance with Medusa on NVIDIA HGX H200 with NVLink Switch

As large language models (LLMs) continue to grow in size and complexity, multi-GPU compute is a must-have to deliver the low latency and high throughput that...

5 MIN READ

Aug 28, 2024

Boosting Llama 3.1 405B Performance up to 1.44x with NVIDIA TensorRT Model Optimizer on NVIDIA H200 GPUs

The Llama 3.1 405B large language model (LLM), developed by Meta, is an open-source community model that delivers state-of-the-art performance and supports a...

7 MIN READ