Related papers: Mitigating Interference of Microservices with a Sc…
Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster.…
Performance analysis is an essential task in High-Performance Computing (HPC) systems and it is applied for different purposes such as anomaly detection, optimal resource allocation, and budget planning. HPC monitoring tasks generate a huge…
Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…
The extensive use of HPC infrastructures and frameworks for running dataintensive applications has led to a growing interest in data partitioning techniques and strategies. In fact, application performance can be heavily affected by how…
Base station clustering is necessary in large interference networks, where the channel state information (CSI) acquisition overhead otherwise would be overwhelming. In this paper, we propose a novel long-term throughput model for the…
Consider media streaming in MIMO interference networks whereby multiple base stations (BS) simultaneously deliver media to their associated users using fixed data rates. The performance is fundamentally limited by the cross-link…
Due to the limited resource capacity of edge servers and the high purchase costs of edge resources, service providers are facing the new challenge of how to take full advantage of the constrained edge resources for Internet of Things (IoT)…
In modern distributed systems, efficient resource allocation is a vital aspect to maintain scalability, reduce operational costs, and ensure fast execution even across heterogeneous workloads. Predictive models for resource usage are…
The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (KV)-related operations, including attention computation and…
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we…
The ever-increasing gap between compute and I/O performance in HPC platforms, together with the development of novel NVMe storage devices (NVRAM), led to the emergence of the burst buffer concept - an intermediate persistent storage layer…
Due to the increasing demand of capacity in wireless cellular networks, the small cells such as pico and femto cells are becoming more popular to enjoy a spatial reuse gain, and thus cells with different sizes are expected to coexist in a…
DL inference queries play an important role in diverse internet services and a large fraction of datacenter cycles are spent on processing DL inference queries. Specifically, the matrix-matrix multiplication (GEMM) operations of…
In this paper, we analyze a multiple-input multiple-output (MIMO) interference channel where nodes are randomly distributed on a plane as a spatial Poisson cluster point process. Each cluster uses interference alignment (IA) to suppress…
Scaling test-time computation--generating and analyzing multiple or sequential outputs for a single input--has become a promising strategy for improving the reliability and quality of large language models (LLMs), as evidenced by advances…
Indexing is an effective way to support efficient query processing in large databases. Recently the concept of learned index, which replaces or complements traditional index structures with machine learning models, has been actively…
With the rapid growth of the data volume and the fast increasing of the computational model complexity in the scenario of cloud computing, it becomes an important topic that how to handle users' requests by scheduling computational jobs and…
Accommodating long-running deep learning (DL) training and inference jobs is challenging on GPU clusters that use traditional batch schedulers, such as Slurm. Given fixed wall clock time limits, DL researchers usually need to run a sequence…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
Recent advancements in Mixed Integer Optimization (MIO) algorithms, paired with hardware enhancements, have led to significant speedups in resolving MIO problems. These strategies have been utilized for optimal subset selection,…