arXiv subjects

Dimitrios Nikolopoulos

Publications and source records attributed to Dimitrios Nikolopoulos.

8 recordsLinked to original sources

arXiv2026

LLM-Guided Runtime Parameter Optimization for Energy-Efficient Model Inference

Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools. As LLMs become integrated into different workflows, different applications have arisen to deal with the challenge of running inference for these tools. This raises another issue of choosing the runtime parameter values for these services in order to minimize the energy consumption. Oftentimes this requires deep knowledge of the application or traditional optimization methods that can take days to find optimal values. In this work, we created a human-in-the-loop flow with LLM-assisted runtime parameter optimization in order to solve this issue. With human-created, specific feedback prompting methods, chat-based LLMs can iteratively find energy-efficient inference parameters faster than traditional search methods. LLMs can also tailor their solutions to different hardware setups and easily take into account other system constraints. The enhanced prompt template was able to converge below the threshold at an average of 3.4 prompts compared to the baseline, which converged in an average of 5.2 prompts, and consistently achieved lower final energy per token. The enhanced prompt template also outperformed Sobol sampling in convergence speed.

cs.SE↗

arXiv2025

Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices

Real-time multi-label video classification on embedded devices is constrained by limited compute and energy budgets. Yet, video streams exhibit structural properties such as label sparsity, temporal continuity, and label co-occurrence that can be leveraged for more efficient inference. We introduce Polymorph, a context-aware framework that activates a minimal set of lightweight Low Rank Adapters (LoRA) per frame. Each adapter specializes in a subset of classes derived from co-occurrence patterns and is implemented as a LoRA weight over a shared backbone. At runtime, Polymorph dynamically selects and composes only the adapters needed to cover the active labels, avoiding full-model switching and weight merging. This modular strategy improves scalability while reducing latency and energy overhead. Polymorph achieves 40% lower energy consumption and improves mAP by 9 points over strong baselines on the TAO dataset. Polymorph is open source at https://github.com/inference-serving/polymorph/.

cs.CV↗

arXiv2025

SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware capabilities. Existing strategies, such as aggressive quantization, pruning, or remote inference, trade accuracy for efficiency or lead to substantial cost burdens. This position paper introduces a new framework that leverages speculative decoding, previously viewed primarily as a decoding acceleration technique for autoregressive generation of LLMs, as a promising approach specifically adapted for edge computing by orchestrating computation across heterogeneous devices. We propose \acronym, a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models, while a single, shared edge server verifies the tokens utilizing a more precise target model. To further increase the efficiency of verification, the edge server batch the diverse verification requests from devices. This approach supports device heterogeneity and reduces server-side memory footprint by sharing the same upstream target model across multiple devices. Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits: 2.2 more system throughput, 2.8 more system capacity, and better cost efficiency, all without sacrificing model accuracy.

cs.DC↗

arXiv2024

Tuning Fast Memory Size based on Modeling of Page Migration for Tiered Memory

Tiered memory, built upon a combination of fast memory and slow memory, provides a cost-effective solution to meet ever-increasing requirements from emerging applications for large memory capacity. Reducing the size of fast memory is valuable to improve memory utilization in production and reduce production costs because fast memory tends to be expensive. However, deciding the fast memory size is challenging because there is a complex interplay between application characterization and the overhead of page migration used to mitigate the impact of limited fast memory capacity. In this paper, we introduce a system, Tuna, to decide fast memory size based on modeling of page migration. Tuna uses micro-benchmarking to model the impact of page migration on application performance using three metrics. Tuna decides the fast memory size based on offline modeling results and limited information on workload telemetry. Evaluating with common big-memory applications and using 5% as the performance loss target, we show that Tuna in combination with a page management system (TPP) saves fast memory by 8.5% on average (up to 16%). This is in contrast to the 5% saving in fast memory reported by Microsoft Pond for the same workloads (BFS and SSSP) and the same performance loss target.

cs.PF↗

arXiv2024

ParvaGPU: Efficient Spatial GPU Sharing for Large-Scale DNN Inference in Cloud Environments

In cloud environments, GPU-based deep neural network (DNN) inference servers are required to meet the Service Level Objective (SLO) latency for each workload under a specified request rate, while also minimizing GPU resource consumption. However, previous studies have not fully achieved this objective. In this paper, we propose ParvaGPU, a technology that facilitates spatial GPU sharing for large-scale DNN inference in cloud computing. ParvaGPU integrates NVIDIA's Multi-Instance GPU (MIG) and Multi-Process Service (MPS) technologies to enhance GPU utilization, with the goal of meeting the diverse SLOs of each workload and reducing overall GPU usage. Specifically, ParvaGPU addresses the challenges of minimizing underutilization within allocated GPU space partitions and external fragmentation in combined MIG and MPS environments. We conducted our assessment on multiple A100 GPUs, evaluating 11 diverse DNN workloads with varying SLOs. Our evaluation revealed no SLO violations and a significant reduction in GPU usage compared to state-of-the-art frameworks.

cs.DC↗

arXiv2023

Towards Persistent Memory based Stateful Serverless Computing for Big Data Applications

The Function-as-a-service (FaaS) computing model has recently seen significant growth especially for highly scalable, event-driven applications. The easy-to-deploy and cost-efficient fine-grained billing of FaaS is highly attractive to big data applications. However, the stateless nature of serverless platforms poses major challenges when supporting stateful I/O intensive workloads such as a lack of native support for stateful execution, state sharing, and inter-function communication. In this paper, we explore the feasibility of performing stateful big data analytics on serverless platforms and improving I/O throughput of functions by using modern storage technologies such as Intel Optane DC Persistent Memory (PMEM). To this end, we propose Marvel, an end-to-end architecture built on top of the popular serverless platform, Apache OpenWhisk and Apache Hadoop. Marvel makes two main contributions: (1) enable stateful function execution on OpenWhisk by maintaining state information in an in-memory caching layer; and (2) provide access to PMEM backed HDFS storage for faster I/O performance. Our evaluation shows that Marvel reduces the overall execution time of big data applications by up to 86.6% compared to current MapReduce implementations on AWS Lambda.

cs.DC↗

arXiv2018

Energy-efficient localised rollback after failures via data flow analysis

Exascale systems will suffer failures hourly. HPC programmers rely mostly on application-level checkpoint and a global rollback to recover. In recent years, techniques reducing the number of rolling back processes have been implemented via message logging. However, the log-based approaches have weaknesses, such as being dependent on complex modifications within an MPI implementation, and the fact that a full restart may be required in the general case. To address the limitations of all log-based mechanisms, we return to checkpoint-only mechanisms, but advocate data-flow-driven recovery (DFR), a fundamentally different approach relying on analysis of the data flow of iterative codes, and the well-known concept of data-flow graphs. We demonstrate the effectiveness of DFR for an MPI stencil code to optimise rollback and reduce the overall energy consumption by 10-12 % on idling nodes during localised rollback. We also provide large-scale estimates for the energy savings of DFR compared to global rollback, which for stencil codes increase as n square for a process count n.

cs.DC↗

arXiv2018

Incremental Training of Deep Convolutional Neural Networks

We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initialization. We demonstrate that our incremental approach reaches the reference network baseline accuracy. Additionally, it allows to identify smaller partitions of the original state-of-the-art network, that deliver the same final accuracy, by using only a fraction of the global number of parameters. This allows for a potential speedup of the training time of several factors. We report training results on CIFAR-10 for ResNet and VGGNet.

cs.LG↗