Dave Salvator

Dave Salvator is a director of product marketing with the NVIDIA Accelerated Computing group. He focuses on hyperscale computing, deep learning, and bringing the NVIDIA data center platform to the cloud.
Avatar photo

Posts by Dave Salvator

An illustration of the NVIDIA H100.
Generative AI / LLMs

Achieving Top Inference Performance with the NVIDIA H100 Tensor Core GPU and NVIDIA TensorRT-LLM

Best-in-class AI performance requires an efficient parallel computing architecture, a productive tool stack, and deeply optimized algorithms. NVIDIA released... 4 MIN READ
An illustration showing the steps "LLM" then "Optimize" then "Deploy."
Generative AI / LLMs

NVIDIA TensorRT-LLM Enhancements Deliver Massive Large Language Model Speedups on NVIDIA H200

Large language models (LLMs) have seen dramatic growth over the last year, and the challenge of delivering great user experiences depends on both high-compute... 5 MIN READ
Illustration representing NeMo Framework.
Generative AI / LLMs

New NVIDIA NeMo Framework Features and NVIDIA H200 Supercharge LLM Training Performance and Versatility

The rapid growth in the size, complexity, and diversity of large language models (LLMs) continues to drive an insatiable need for AI training performance.... 9 MIN READ
Image of Infiniband with decorative images in front.

New MLPerf Inference Network Division Showcases NVIDIA InfiniBand and GPUDirect RDMA Capabilities

In MLPerf Inference v3.0, NVIDIA made its first submissions to the newly introduced Network division, which is now part of the MLPerf Inference Datacenter... 9 MIN READ
Simulation / Modeling / Design

Getting the Best Performance on MLPerf Inference 2.0

Models like Megatron 530B are expanding the range of problems AI can address. However, as models continue to grow complexity, they pose a twofold challenge for... 11 MIN READ

AWS Launches First NVIDIA GPU-Accelerated Graviton-Based Instance with Amazon EC2 G5g

Today at AWS re:Invent 2021, AWS announced the general availability of Amazon EC2 G5g instances—bringing the first NVIDIA GPU-accelerated Arm-based instance... 3 MIN READ