A new update for Nvidia ChatRTX, Nvidia’s visual computing platform that offers real time, cinematic-quality rendering to game developers, is available for download today. The update expands the tech demo’s capabilities and supported LLM models for RTX-enabled AI applications.
First announced and shown off at GTC 2024 earlier in March, the update adds several new capabilities. ChatRTX now has a bigger list of supported LLMs, including Gemma, Google’s latest LLM, and ChatGLM3, an open, bilingual (English and Chinese) LLM, providing users with additional flexibility.
New photo support enables ChatRTX users to easily search and interact locally with their own photo data without the need for complex metadata labeling, thanks to OpenAI’s Contrastive Language-Image Pre-training (CLIP).
ChatRTX users can now speak with their own data, with added support for Whisper, an AI automatic speech recognition system that now enables ChatRTX to understand verbal speech.
ChatRTX enables users to unleash the power of AI on their RTX-powered PCs today, leveraging the accelerated performance of TensorRT-LLM software and NVIDIA RTX. And it’s all done locally on your PC, so your data is secure. Moreover, it’s available on GitHub as a free reference project, enabling developers to explore and expand AI applications using RAG technology for even more diverse use cases.
You can find more information in the embargoed AI Decoded blog, along with a new update for the RTX Remix beta that adds DLSS 3.5 with Ray Reconstruction.