NVIDIA has introduced Ising, its newest OpenAI models designed to make Quantum Computers useful and faster with brand new capabilities.
NVIDIA Ising AI Models For Quantum Computers Bring Up To 3x Performance Boost
Quantum Computing has been cited as the next frontier of computing for decades. Several companies have been trying to perfect quantum computing for years now, and only now have a few started to break the code.
NVIDIA already offers an open-source development platform for quantum computing called CUDA-Q. The platform is "qubit-agnostic" and works seamlessly with QPUs and Qubit Modalities.
Today, NVIDIA is announcing its first family of open source quantum AI models, called Ising. The new model is designed to help researchers and enterprises build quantum processors that are not only capable but also useful for running applications, AI in specific.
But the main bottleneck in quantum computing currently stems from quantum processor calibration and quantum error correction. Qubits are noisy and have many errors. Currently, Quantum processors produce an error once every thousand operations, but for Quantum Computers to become more practical, this needs to be reduced to once every trillion operations. NVIDIA says that AI is the key to eliminating this bottleneck and enabling quantum processors for large-scale, reliable computing.
Ising includes two "state-of-the-art" and customizable models.
- Ising Calibration: A vision language model that can rapidly interpret and react to measurements from quantum processors, enabling AI agents to automate continuous calibration, reducing the time needed from days to hours.
- Ising Decoding: Two variants of a 3D convolutional neural network model — optimized for either speed or accuracy — to perform real-time decoding for quantum error correction. Ising Decoding models are up to 2.5x faster and 3x more accurate than pyMatching, the current open source industry standard.
As per NVIDIA, these Ising models offer 2.5x faster performance and 3x higher accuracy for the decoding process, a crucial step required for quantum error correction. What is also interesting is the fact that Ising Calibration is 15x smaller than alternatives, while Ising Decoding requires 10x lower data to train.
NVIDIA confirms that its Ising open AI models are currently being used by leading researchers, academic institutions, and enterprises. Once again, this is just one step ahead in the Quantum Computing era.
About the author: A Software Engineer by training and a PC enthusiast by passion, Hassan Mujtaba serves as Wccftech's Senior Editor for hardware section. With years of experience in the industry, he specializes in deep-dive technical analysis of next-generation CPU and GPU architectures, motherboards, and cooling solutions. His work involves not only breaking news on upcoming technologies but also extensive hands-on reviews and benchmarking.
Follow Wccftech on Google to get more of our news coverage in your feeds.
