Related papers: Virtual-Link: A Scalable Multi-Producer, Multi-Con…
We consider the problem of providing service guarantees in a high-speed packet switch. As basic requirements, the switch should be scalable to high speeds per port, a large number of ports and a large number of traffic flows with…
Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table…
Wireless communications using light waves are called visible light communication. A technique called Physical-layer Network coding allows several users to communicate simultaneously over the same channel in a distributed space-time Coding…
The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading the massive KV-Cache from external storage creates a…
Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…
Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…
This article proposes a novel virtualized air interface protocol stack for next-generation wireless networks, that natively supports multiple radio access technologies and multi-point transmissions. Leveraging upon the concepts of…
A three-dimensional (3D) Network-on-Chip (NoC) enables the design of high performance and low power many-core chips. Existing 3D NoCs are inadequate for meeting the ever-increasing performance requirements of many-core processors since they…
Emerging intelligent service scenarios in 6G communication impose stringent requirements for low latency, high reliability, and privacy preservation. Generative large language models (LLMs) are gradually becoming key enablers for the…
To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a…
Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…
Vehicular Ad Hoc Network has attracted both research and industrial community due to its benefits in facilitating human life and enhancing the security and comfort. However, various issues have been faced in such networks such as…
Existing network stacks tackle performance and scalability aspects by relying on multiple receive queues. However, at software level, each queue is processed by a single thread, which prevents simultaneous work on the same queue and limits…
Improving the throughput of molecular docking, a computationally intensive phase of the virtual screening process, is a highly sought area of research since it has a significant weight in the drug designing process. With such improvements,…
Distributed multi-task learning (DMTL) effectively improves model generalization performance through the collaborative training of multiple related models. However, in large-scale learning scenarios, communication bottlenecks severely limit…
Cellular Vehicle-to-Everything (C-V2X) technology promises to provide ultra-reliable low latency communication (URLLC) framework for connected vehicles. Connected vehicles can help us improve traffic safety, congestion and reduce fatal…
Virtualization is the abstraction of details. Algorithms and programming languages provide abstraction, too. Virtualization of hardware and embedded systems is becoming more and more important in heterogeneous environments and networks,…
Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language…
An important ingredient of the future 5G systems will be Ultra-Reliable Low-Latency Communication (URLLC). A way to offer URLLC without intervention in the baseband/PHY layer design is to use interface diversity and integrate multiple…
Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…