Joseph Loftin

Joseph Loftin is a deep learning software inference engineer on the NVIDIA TensorRT team. His work focuses on enabling and optimizing multi-device inference through graph parallelism implementations, compiler enhancements, distributed collective development, and specialized kernels. He holds a master’s degree in computer science from Georgia Institute of Technology and a bachelor’s degree in electrical engineering from the University of Louisiana at Lafayette.
Avatar photo

Posts by Joseph Loftin

Agentic AI / Generative AI

Simplifying Model Serving Across Multiple GPUs with NVIDIA TensorRT Multi-Device Integration in NVIDIA Dynamo-Triton

The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability... 7 MIN READ
Developer Tools & Techniques

Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support

Generative AI workloads are rapidly outgrowing the memory and compute budget of single GPUs. For inference developers building media generation pipelines, the... 11 MIN READ