Related papers: Analyzing Reverse Address Translation Overheads in…

The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can…

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these subnetworks is not…

This study investigates the capabilities of Large Language Models (LLMs), specifically GPT-4, in the context of Binary Reverse Engineering (RE). Employing a structured experimental approach, we analyzed the LLM's performance in interpreting…

This paper studies strategies to optimize the lane configuration of a transportation network for a given set of Origin-Destination demands using a planning macroscopic network flow model. The lane reversal problem is, in general, NP-hard…

Robustness, the ability of models to maintain performance in the face of perturbations, is critical for developing reliable NLP systems. Recent studies have shown promising results in improving the robustness of models through adversarial…

Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing…

Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…

The rise of Large Language Models (LLMs) has redefined Machine Translation (MT), enabling context-aware and fluent translations across hundreds of languages and textual domains. Despite their remarkable capabilities, LLMs often exhibit…

Multilingual Machine Translation promises to improve translation quality between non-English languages. This is advantageous for several reasons, namely lower latency (no need to translate twice), and reduced error cascades (e.g., avoiding…

Large language models (LLMs) have achieved significant success across various domains. However, training these LLMs typically involves substantial memory and computational costs during both forward and backward propagation. While…

The all-to-all collective communications primitive is widely used in machine learning (ML) and high performance computing (HPC) workloads, and optimizing its performance is of interest to both ML and HPC communities. All-to-all is a…

In this paper we propose and implement novel techniques for performance evaluation of web traffic (response time, response code, etc.), with no reassembly of the underlying TCP connection, which severely restricts the traffic analysis…

To keep up with demand, servers will scale up to handle hundreds of thousands of clients simultaneously. Much of the focus of the community has been on scaling servers in terms of aggregate traffic intensity (packets transmitted per…

Efficient large-scale inference of transformer-based large language models (LLMs) remains a fundamental systems challenge, frequently requiring multi-GPU parallelism to meet stringent latency and throughput targets. Conventional tensor…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

The performance of a parallel algorithm in a very large scale grid is significantly influenced by the underlying Internet protocols and inter-connectivity. Many grid programming platforms use TCP due to its reliability, usually with some…

Modern AI workloads such as large language models (LLMs) and retrieval-augmented generation (RAG) impose severe demands on memory, communication bandwidth, and resource flexibility. Traditional GPU-centric architectures struggle to scale…

Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-utilized concurrency. In practice, 80-95% of requests are short, yet are served under…

In this paper, we analyze the performance of random load resampling and migration strategies in parallel server systems. Clients initially attach to an arbitrary server, but may switch server independently at random instants of time in an…

Network address translation (NAT) is a basic functionality in cloud gateways. With the increasing traffic volume and number of flows introduced by the cloud tenants, the NAT gateway needs to be implemented on a cluster of servers. We…