NVIDIA, today, declared a groundbreaking advancement in computing with the introduction of GeForce RTX SUPER desktop GPUs, a fleet of AI-powered laptops from major manufacturers, and NVIDIA RTX-enhanced AI software and tools, catering to both developers and consumers.
Pioneering a new era in PC capabilities, NVIDIA leverages its expertise in the PC technology, with over 100 million RTX GPUs powering the AI PC revolution. These tools are set to elevate PC experiences with generative AI:
NVIDIA’s AI Workbench, a user-friendly toolkit for AI developers, is set to enter its beta phase later this month, simplifying AI model creation and customization.
The NVIDIA TensorRT-LLM (TRT-LLM), an open-source library designed to accelerate and optimize inference performance for large language models (LLMs), now supports a broader array of pre-optimized models for PCs, fostering enhanced AI interactions, such as the upcoming release of Chat with RTX tech demo.
The introduction of RTX AI PCs and Workstations, powered by NVIDIA RTX GPUs, empowers generative AI performance on PCs, prioritizing privacy, low latency, and cost efficiency for diverse applications.
The new GeForce RTX 40 SUPER Series graphics cards, including models like the GeForce RTX 4080 SUPER and others, promise remarkable AI video and image generation speeds compared to their predecessors, leveraging Tensor Cores for transformative AI capabilities in gaming, content creation, and productivity.
AI-Powered Laptops and Workstations:
Leading manufacturers like Acer, ASUS, Dell, HP, Lenovo, MSI, Razer, and Samsung are set to launch a fresh lineup of RTX AI laptops, offering users comprehensive generative AI capabilities right out of the box.
RTX GPU-equipped mobile workstations are primed to support NVIDIA AI Enterprise software, including TensorRT and NVIDIA RAPIDS, enabling simplified and secure generative AI and data science development.
NVIDIA AI Workbench, debuting in beta soon, streamlines access to popular repositories, facilitating swift creation and customization of AI models.
Collaboration with HP integrates NVIDIA AI Foundation Models and Endpoints into the HP AI Studio, simplifying AI model deployment across PCs and the cloud.
Enhanced AI Model Development:
TensorRT-LLM for Windows accelerates text-based applications, boasting significant speed advantages in inference backends for optimized models on PCs.
NVIDIA’s concerted efforts span the entire technology spectrum, promising a new realm of experiences and building upon the extensive array of AI-enabled applications and games accelerated by NVIDIA RTX technology. The focus on local AI processing on PCs underscores NVIDIA’s commitment to privacy, low latency, and tailored AI experiences for the evolving demands of users across industries.