Demo: Optimizing Gemma inference on NVIDIA GPUs with TensorRT-LLM

Even the smallest of Large Language Models are compute intensive significantly affecting the cost of your Generative AI application. Your ability to increase the throughput and reduce latency can make or break many business cases. NVIDIA TensorRT-LLM is an open-source tool that allows you to considerably speed up execution of your models and in this talk we will demonstrate its application to Gemma.
Checkout more videos of Gemma Developer Day 2024 → goo.gle/440EAIV
Subscribe to Google for Developers → goo.gle/developers
#Gemma #GemmaDeveloperDay
Event: Gemma Developer Day 2024

[@LuigiGoogle]

hello google, I am inspired by your company, could you create open source projects to work with people who are also interested in this, namely this topic of neural networks.

[@shayantriedcoding]

Hi, I am Shayan, beginner Python developer, I want to learn something from code jams or online coding challenges, can Google team will do that work for me please 🥺, I really want to learn something from Google code jam.