Related papers: KnapsackLB: Enabling Performance-Aware Layer-4 Loa…
The rapid adoption of large language models (LLMs) has shifted a substantial portion of inference workloads into throughput-oriented offline regimes, where fully utilizing GPU compute requires large batch sizes. However, existing…
Software-defined networking (SDN) and software-defined flash (SDF) have been serving as the backbone of modern data centers. They are managed separately to handle I/O requests. At first glance, this is a reasonable design by following the…
Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent…
In order to utilize network resources and provide a more reliable delivery of information, multipath routing algorithms are used with a higher priority than single path routing. But providing the quality of service (QoS) requirements while…
Transformer-based large language models (LLMs) are increasingly being adopted in networking research to address domain-specific challenges. However, their quadratic time complexity and substantial model sizes often result in significant…
In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backward computation. However, despite empirical success, a…
Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…
Structured pruning can simplify network architecture and improve inference speed. Combined with the underlying hardware and inference engine in which the final model is deployed, better results can be obtained by using latency collaborative…
Nowadays, centralized Path Computation Elements (PCE) integrate control plane algorithms to optimize routing and load-balancing continuously. When a link fails, the traffic load is automatically transferred to the remaining paths according…
On the Internet, sub-millisecond queueing delay and capacity-seeking have traditionally been considered mutually exclusive. We introduce a service that offers both: Low Latency Low Loss Scalable throughput (L4S). When tested under a wide…
To overcome long propagation delays for data exchange between the remote cloud data center and end devices in Mobile Cloud Computing (MCC), Mobile Edge Computing (MEC) is merging to push mobile computing, network control and storage to the…
We introduce Dynaboard, an evaluation-as-a-service framework for hosting benchmarks and conducting holistic model comparison, integrated with the Dynabench platform. Our platform evaluates NLP models directly instead of relying on…
Embedding fusion has emerged as an effective approach for enhancing performance across various NLP tasks. However, systematic guidelines for selecting optimal layers and developing effective fusion strategies for the integration of LLMs…
With 5G networking, deterministic guarantees are emerging as a key enabler. In this context, we present a scalable Damper-based architecture for Large-scale Deterministic IP Networks (D-LDN) that meets required bounds on end-to-end delay…
This paper studies the sensitivity (or insensitivity) of a class of load balancing algorithms that achieve asymptotic zero-waiting in the sub-Halfin-Whitt regime, named LB-zero. Most existing results on zero-waiting load balancing…
The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…
Network load balancers are central components in data centers, that distributes workloads across multiple servers and thereby contribute to offering scalable services. However, when load balancers operate in dynamic environments with…
NLP Workbench is a web-based platform for text mining that allows non-expert users to obtain semantic understanding of large-scale corpora using state-of-the-art text mining models. The platform is built upon latest pre-trained models and…
Sequence parallelism (SP) serves as a prevalent strategy to handle long sequences that exceed the memory limit of a single device. However, for linear sequence modeling methods like linear attention, existing SP approaches do not take…
This paper introduces a novel computational approach for offloading sensor data processing tasks to servers in edge networks for better accuracy and makespan. A task is assigned with one of several offloading options, each comprises a…