At IEEE Quantum Week 2026 in Toronto, Quandela is demonstrating a pathway to integrate quantum processors into existing artificial intelligence and high-performance computing infrastructure using NVIDIA’s NVQLink, the company says. The collaboration focuses on a three-step approach, access, integration and discovery, and scale, allowing organizations to explore quantum applications without replacing current systems.
Algorithms can be developed and simulated on NVIDIA GPUs before deployment on Quandela’s photonic quantum processing unit, positioning the QPU as a specialized accelerator. “The challenge is no longer just about accessing a QPU, but about integrating it directly into AI workflows,” says Jean Senellart, Chief Technology and Product Officer at Quandela, as the companies are publishing a technical white paper outlining this hybrid architecture.
Photonic QPU Integration with NVIDIA NVQLink for AI Workflows
NVIDIA’s NVQLink enables a low-latency connection under 4 microseconds between the NVIDIA GPU environment and the Quantum System Controller, a critical advancement detailed in a new technical white paper published by Quandela and NVIDIA. This low-latency link facilitates direct communication, enabling the GPU to orchestrate quantum workloads executed on the photonic QPU, rather than relying on slower conventional interfaces. This phased integration strategy allows developers to use existing GPU infrastructure and software ecosystems, such as the NVIDIA CUDA-Q platform and cuQuantum SDK, for algorithm development and simulation before deployment on actual quantum hardware.
Algorithms are first refined on GPUs, mitigating the challenges of early-stage quantum processor limitations and accelerating the development cycle, according to the company. “Quantum computing becomes more useful when it moves beyond standalone access and becomes part of the accelerated computing researchers already use,” said Sam Stanwyck, Director of Quantum Product at NVIDIA.
“Our work with Quandela provides a step-by-step model for bringing photonic QPUs into NVIDIA quantum-GPU supercomputing, helping teams identify promising applications today and scale them as more powerful systems come online.” The collaborative approach outlined by Quandela and NVIDIA emphasizes the complementarity of CPUs, GPUs, and QPUs, assigning each a specific role within the overall computational workflow. CPUs manage the orchestration of tasks, GPUs handle intensive computation and simulation, and the QPU accelerates quantum-specific algorithms.
This architecture, presented at IEEE Quantum Week 2026 in Toronto at the NVIDIA booth (#600), aims to reduce the barriers to entry for quantum computing by allowing organizations to build upon their existing HPC infrastructure. The companies’ joint publication details this hybrid computing model, combining GPU and QPU capabilities to create new opportunities in AI and scientific discovery, and will be available to attendees.
Quantum computing becomes more useful when it moves beyond standalone access and becomes part of the accelerated computing researchers already use. Our work with Quandela provides a step-by-step model for bringing photonic QPUs into NVIDIA quantum-GPU supercomputing, helping teams identify promising applications today and scale them as more powerful systems come online.
Sam Stanwyck, Director of Quantum Product at NVIDIA
Three-Step Approach: Access, Integration & Scale for Quantum Adoption
The collaborative architecture detailed by Quandela and NVIDIA prioritizes a phased implementation, beginning with readily available resources before progressing to tightly integrated systems. This strategy acknowledges that widespread quantum adoption hinges not solely on hardware advancements, but on a practical pathway for existing computational infrastructure to incorporate quantum processing capabilities. The Integration & Discovery phase centers on using the strengths of both classical and quantum processors, with GPUs handling intensive computation and simulation while the QPU functions as a targeted accelerator. Scale aims to expand applications that have demonstrated their potential toward larger, more powerful quantum systems. “This approach allows users to progress step by step toward quantum computing,” the companies state in their joint publication, “building on their existing infrastructure and developing new capabilities as high-potential applications are identified.” This incremental approach contrasts with attempts to immediately replace classical infrastructure, instead focusing on augmenting it with quantum capabilities where they offer a demonstrable benefit. The companies’ vision, unveiled at the conference, suggests a future where quantum processors are seamlessly integrated into existing AI and HPC environments, enhancing rather than disrupting current workflows.
The challenge is no longer just about accessing a QPU, but about integrating it directly into AI workflows. With NVIDIA, we are opening a path where the photonic QPU becomes a specialized accelerator for exploring and validating hybrid algorithms, particularly in QML, before scaling the most promising use cases.
Sam Stanwyck, Director of Quantum Product at NVIDIA
See today’s quantum computing news on Quantum Zeitgeist for the latest breakthroughs in qubits, hardware, algorithms, and industry deals.
