NVIDIA CUDA Quantum

The platform for hybrid quantum-classical computing.

To do algorithm research and build applications for future quantum advantage, a bridging technology is needed to enable dynamic workflows across disparate system architectures. With a unified and open programming model, NVIDIA CUDA Quantum is a first-of-its-kind, open-source platform for integrating and programming quantum processing units (QPUs), GPUs, and CPUs in one system. NVIDIA CUDA Quantum enables GPU-accelerated system scalability and performance across heterogeneous QPU, CPU, GPU, and emulated quantum system elements.


Get Started
NVIDIA CUDA Quantum framework
NVIDIA CUDA Quantum consists of both a specification and a compiler NVQ++. It delivers a unified programming model designed for quantum processors (either actual or emulated) in a hybrid setting—that is, CPUs, GPUs, and QPUs working together.

Key Benefits

NVIDIA CUDA Quantum is flexible and scalable

Flexible and Scalable

Supports hybrid deployments via emulation on a single GPU up to NVIDIA DGX SuperPOD™and with multiple QPU partner backends

NVIDIA CUDA Quantum is an open platform

Open Platform

Connects to any type of QPU backend, allowing accessibility to all users

 NVIDIA CUDA Quantum is high performing

High Performing

287X speedup in end-to-end Variational Quantum Eigensolver (VQE) performance with 20 qubits and dramatically improved scaling compared to Pythonic frameworks

NVIDIA CUDA Quantum can be easily integrated with modern GPU-accelerated apps

Easily Integrated

Interoperates with modern GPU-accelerated applications

NVIDIA CUDA Quantum improves productivity and scalability in quantum algorithm research

Productive

Streamlines hybrid quantum-classical development with a unified environment, improving productivity and scalability in quantum algorithm research

A Range of Features

  • Kernel-based programming model extending C++ and Python for hybrid quantum-classical systems
  • Native support for GPU hybrid compute, enabling GPU pre- and post-processing and classical optimizations
  • System-level compiler toolchain featuring split compilation with NVQ++ compiler for quantum kernels, lowering to Multi-Level Intermediate Representation (MLIR) and Quantum Intermediate Representation (QIR)
  • Initial NVQ++ benchmark shows 287X improvement in end-to-end VQE performance with 20 qubits and dramatically improved scaling with system size compared to standard Pythonic implementation
  • Standard library of quantum algorithmic primitives
  • Interoperable with partner QPUs as well as simulated QPUs using the cuQuantum GPU platform; partnering with QPU builders across many different qubit types

Integrated Quantum Processors

NVIDIA CUDA Quantum enables straightforward execution of hybrid code on many different types of quantum processors, simulated or physical. Researchers can leverage the cuQuantum-accelerated simulation backend as well as QPUs from our partners or connect their own simulator or quantum processor. The image shows the variational quantum eigensolver running on both cuQuantum and Quantinuum’s H1 trapped ion QPU. Switching between the two is as simple as changing a compiler flag.

Variational quantum eigensolver running on both cuQuantum and Quantinuum’s H1 trapped ion QPU

Quantum Computing Partners

Quantum Computing Partner - Atom Computing
Quantum Computing Partner - Classiq
Quantum Computing Partner - IQM
Quantum Computing Partner - Julich
Quantum Computing Partner - NERSC
Quantum Computing Partner - Oxford Quantum Circuits
Quantum Computing Partner - Orca Computing
Quantum Computing Partner - Oak Ridge National Laboratory
Quantum Computing Partner - Pasqal
Quantum Computing Partner - Quantinuum
Quantum Computing Partner - Quantum Brilliance
Quantum Computing Partner - QCWare
Quantum Computing Partner - Rigetti
Quantum Computing Partner - Xanadu
Quantum Computing Partner - Zapata

Get started with CUDA Quantum today.

Get Started