From Model Weights to API Endpoint with TensorRT LLM

Learn to deploy high-performance large language models using TensorRT-LLM in this comprehensive workshop recorded at the AI Engineer World's Fair. Master the complete pipeline from selecting and optimizing models to building TensorRT-LLM engines, configuring batch sizes and sequence lengths, and deploying on cloud GPUs. Discover how to overcome the steep learning curve of TensorRT-LLM while achieving significant performance gains in production environments. Gain practical insights from industry experts Philip Kiely and Pankaj Gupta, who share their real-world experience running TensorRT and TensorRT-LLM in production systems, including both the incredible performance benefits and common implementation challenges you'll encounter when getting started with this powerful model serving framework.