TensorRT accelerates AI on RTX PCs by enabling fully optimized AI experiences, doubling AI performance, and accelerating popular generative AI models. It also offers advantages such as lower latency, cost savings, always-on access to AI capabilities, and data privacy. TensorRT-LLM is an open-source library that optimizes LLM inference and supports popular community models. ChatRTX is a tech demo that demonstrates the performance of different models running locally on Windows PC.
Table of contents
More Efficient and Precise AIOther Popular Apps Accelerated by TensorRTOptimized for LLMsShare this post