CQN is developing the entire technology stack to reliably carry quantum data across the globe, serving diverse applications across many user groups simultaneously... spurring new technology industries and a competitive marketplace of quantum service providers and application developers.
On Monday, September 30 2024, the 4th floor of the Grand Challenges Research Building at the University of Arizona, hosted an open house. The goal was to create a community around the quantum research happening at the University of Arizona. In attendance was Ford Burkhart who wrote a lovely piece on the event and work […]
We’re pleased to release the dates for our 2025 Winter School on Quantum Networks. Keep an eye out for the registration to open soon! All courses will be held via Zoom, co-taught by CQN faculty, postdocs and students.
Join us for a World Quantum Day panel organized jointly by the Perimeter Institute and Quantum Ethics Project and sponsored by CQN. Our discussion will feature Raymond LaFlamme (Institute for Quantum Computing), Zeki Seskir (Karlsruhe Institute of Technology (KIT)) Jean Olemou (Leap Quantik) Taqi Raza (Center for Quantum Networks) and Joan Arrow (Quantum Ethics Project, Center for Quantum Networks). The panel will discuss how […]
Narayanan Rengaswamy is a an assistant professor in the Electrical and Computer Engineering program at the University of Arizona.He also works at the NSF Engineering Research Center for Quantum Networks (CQN) in the university. He discusses his research focuses on quantum error correction and fault tolerance.
Optica Quantum is a new online-only journal dedicated to high-impact results in quantum information science and technology (QIST), as enabled by optics and photonics. Optica Quantum will publish its first issue in September 2023. Its scope will encompass theoretical and experimental research as well as technological advances in and applications of quantum optics. In addition, the Journal will […]
We are pleased to announce the appointment of Julie Des Jardins as the new Director for Diversity and Culture of Inclusion (DCI) within CQN. Dr. Des Jardins is a cultural historian, educator, and DEI practitioner who examines gender, race, and intersectional identity in American culture, particularly in academia, athletics, politics, and STEM. She has also […]
A short video highlighting CQN’s work in building the quantum Internet was featured at the American Physical Society (APS) meeting in Las Vegas in March 2023. The six-minute video features laboratory footage from multiple CQN campuses and interviews with director Saikat Guha, as well as investigators Linran Fan, Dirk Englund, Jane Bambauer, Don Towsley, and […]
All nine courses can be found on our YouTube channel in the CQN Winter School for Quantum Networks playlist. Slides associated with the courses can be found here.
Check out additional stories and events from the Center for Quantum Networks.
Large language models (LLMs) have been a disruptive innovation in recent
years, and they play a crucial role in our daily lives due to their ability to
understand and generate human-like text. Their capabilities include natural
language understanding, information retrieval and search, translation,
chatbots, virtual assistance, and many more. However, it is well known that
LLMs are massive in terms of the number of parameters. Additionally, the
self-attention mechanism in the underlying architecture of LLMs, Transformers,
has quadratic complexity in terms of both computation and memory with respect
to the input sequence length. For these reasons, LLM inference is
resource-intensive, and thus, the throughput of LLM inference is limited,
especially for the longer sequences. In this report, we design a collaborative
inference architecture between a server and its clients to alleviate the
throughput limit. In this design, we consider the available resources on both
sides, i.e., the computation and communication costs. We develop a dynamic
programming-based algorithm to optimally allocate computation between the
server and the client device to increase the server throughput, while not
violating the service level agreement (SLA). We show in the experiments that we
are able to efficiently distribute the workload allowing for roughly 1/3
reduction in the server workload, while achieving 19 percent improvement over a
greedy method. As a result, we are able to demonstrate that, in an environment
with different types of LLM inference requests, the throughput of the server is
improved.
Large language models (LLMs) have been a disruptive innovation in recent
years, and they play a crucial role in our daily lives due to their ability to
understand and generate human-like text. Their capabilities include natural
language understanding, information retrieval and search, translation,
chatbots, virtual assistance, and many more. However, it is well known that
LLMs are massive in terms of the number of parameters. Additionally, the
self-attention mechanism in the underlying architecture of LLMs, Transformers,
has quadratic complexity in terms of both computation and memory with respect
to the input sequence length. For these reasons, LLM inference is
resource-intensive, and thus, the throughput of LLM inference is limited,
especially for the longer sequences. In this report, we design a collaborative
inference architecture between a server and its clients to alleviate the
throughput limit. In this design, we consider the available resources on both
sides, i.e., the computation and communication costs. We develop a dynamic
programming-based algorithm to optimally allocate computation between the
server and the client device to increase the server throughput, while not
violating the service level agreement (SLA). We show in the experiments that we
are able to efficiently distribute the workload allowing for roughly 1/3
reduction in the server workload, while achieving 19 percent improvement over a
greedy method. As a result, we are able to demonstrate that, in an environment
with different types of LLM inference requests, the throughput of the server is
improved.
Designing an operational architecture for the Quantum Internet is a
challenging task in light of both fundamental limitations imposed by the laws
of physics and technological constraints. Here, we propose a method to abstract
away most of the quantum-specific elements and formulate a best-effort quantum
network architecture based on packet-switching, akin to that of the classical
Internet. Such reframing provides an opportunity to exploit the many tools and
protocols available and well-understood within the Internet. As an
illustration, we tailor and adapt classical congestion control and active queue
management protocols to quantum networks, comprising an architecture wherein
quantum end- and intermediate nodes effectively regulate demand and resource
utilization, respectively. Results show that these classical networking tools
can be effectively used to combat quantum memory decoherence and keep
end-to-end fidelity around a target value.
Understanding quantum noise is an essential step towards building practical
quantum information processing systems. Pauli noise is a useful model that has
been widely applied in quantum benchmarking, error mitigation, and error
correction. Despite intensive study, most existing works focus on learning
Pauli noise channels associated with some specific gates rather than treating
the gate set as a whole. A learning algorithm that is self-consistent,
complete, and efficient at the same time is yet to be established. In this
work, we study the task of gate set Pauli noise learning, where a set of
quantum gates, state preparation, and measurements all suffer from unknown
Pauli noise channels with a customized noise ansatz. Using tools from algebraic
graph theory, we analytically characterize the self-consistently learnable
degrees of freedom for Pauli noise models with arbitrary linear ansatz, and
design experiments to efficiently learn all the learnable information.
Specifically, we show that all learnable information about the gate noise can
be learned to relative precision, under mild assumptions on the noise ansatz.
We then demonstrate the flexibility of our theory by applying it to concrete
physically motivated ansatzs (such as spatially local or quasi-local noise) and
experimentally relevant gate sets (such as parallel CZ gates). These results
not only enhance the theoretical understanding of quantum noise learning, but
also provide a feasible recipe for characterizing existing and near-future
quantum information processing devices.
See all the latest pre-published papers from our team of collaborators.
