AI Perf benchmarking - Dynamo and other LLM endpoints

​Join us as we cover features of Dynamo and walk you through a hands-on demo. See how Dynamo accelerates inference for LLMs across your preferred hardware and integrates smoothly with popular tools like PyTorch, TensorRT-LLM, and vLLM.​​

We'll cover AIPerf - a comprehensive benchmarking tool that measures the performance of generative AI models served by your chosen inference solution. It provides detailed performance metrics from command-line displays to extensive reports allowing you to compare and optimize your models effectively for real-world deployment.​

Ready to try it out? Explore the code, start your own experiments, and contribute to the project! Check out the NVIDIA Dynamo GitHub repo: http://github.com/ai-dynamo

#NVIDIADynamo #AIInference #OpenSourceAI #AIPerf #GenerativeAI