Related papers: Avoiding Cross-Datacenter Collective Congestion vi…

Data processing frameworks such as Apache Beam and Apache Spark are used for a wide range of applications, from logs analysis to data preparation for DNN training. It is thus unsurprising that there has been a large amount of work on…

In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. To prevent performance interference between the two phases, current…

ML workloads are becoming increasingly popular in the cloud. Good cloud training performance is contingent on efficient parameter exchange among VMs. We find that Collectives, the widely used distributed communication algorithms, cannot…

Autoregressive inference in large transformer-based language models (LLMs) presents significant challenges for runtime efficiency, particularly during the decode phase where load imbalance across GPU shards can cause throughput degradation…

Learning-based congestion control (CC), including Reinforcement-Learning, promises efficient CC in a fast-changing networking landscape, where evolving communication technologies, applications and traffic workloads pose severe challenges to…

Emerging distributed cloud architectures, e.g., fog and mobile edge computing, are playing an increasingly important role in the efficient delivery of real-time stream-processing applications (also referred to as augmented information…

Software Defined Vehicles face an increasing computational gap as advanced algorithms and frequent software updates demand more processing power while onboard hardware remains static throughout a vehicle's 10+ year lifespan. This mismatch…

In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Learning (CL) focuses…

This paper is focused on the problem of optimizing the aggregate throughput of the Distributed Coordination Function (DCF) employing the basic access mechanism at the data link layer of IEEE 802.11 protocols. In order to broaden the…

Data Loss/Leakage Prevention (DLP) continues to be the main issue for many large organizations. There are multiple numbers of emerging security attach scenarios and a limitless number of overcoming solutions. Today's enterprises' major…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level…

The goal of congestion control is to avoid congestion in network elements. A network element is congested if it is being offered more traffic than it can process. To detect such situations and to neutralize them we should monitor traffic in…

Multipath TCP (MPTCP) has emerged as a facilitator for harnessing and pooling available bandwidth in wireless/wireline communication networks and in data centers. Existing implementations of MPTCP such as, Linked Increase Algorithm (LIA),…

Congestion control is a fundamental component of Internet infrastructure, and researchers have dedicated considerable effort to developing improved congestion control algorithms. However, despite extensive study, existing algorithms…

The rapid growth in the size of large language models has necessitated the partitioning of computational workloads across accelerators such as GPUs, TPUs, and NPUs. However, these parallelization strategies incur substantial data…

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…

Monitoring the dynamics of traffic in major corridors can provide invaluable insight for traffic planning purposes. An important requirement for this monitoring is the availability of methods to automatically detect major traffic events and…

Graph-based computations are crucial in a wide range of applications, where graphs can scale to trillions of edges. To enable efficient training on such large graphs, mini-batch subgraph sampling is commonly used, which allows training…

Streaming analytics are essential in a large range of applications, including databases, networking, and machine learning. To optimize performance, practitioners are increasingly offloading such analytics to network nodes such as switches.…

State of art DL models are growing in size and complexity, with many modern models also increasing in heterogeneity of behavior. GPUs are still the dominant platform for DL applications, relying on a bulk-synchronous execution model which…