Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 30 for “"Model Serving"”.
-
A large-scale model serving framework
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01
-
Multi-tenant Machine Learning Model Serving Systems on GPU Clusters
… GPUs are both costly and scarce, efficiently serving machine learning models has become a critical challenge. Assuming that serving one model requires $k$ GPUs, serving n models would seemingly require $kn$ GPUs. In the multi-tenant setting, we can pool the whole cluster's GPUs to serve the …
-
Building and Accelerating a Declarative Platform for Machine Learning Model Serving
… engines to bear for scalable machine learning model serving. Much work remains in AI + systems; advances for each of the subproblems will be applicable to end applications and will lead to better user experiences as well as less cost.
-
Assessment of a technical assistance model: Serving youth with disabilities in residential settings in North Dakota.
… and treatment facilities and school districts in serving these youth.The purpose of this study was to identify if a technical assistance project could facilitate interaction among educators from disparate agencies. The project was evaluated in relation to a model for technical assistance developed …
-
Retrospective analysis of healthcare utilization and expenditures associated with an integrated, care coordination model serving Medicaid-eligible children with medical complexities
… effects of a pediatrician-led care coordination model (PLCM) versus usual, standard pediatric care (SPC) on health utilization and expenditure patterns in a randomized cohort of Medicaid-eligible children with medical complexities (CMC). Methods: Retrospective secondary database analysis of Texas …
-
Development and Implementation of Control System for an Advanced Multi-Regime Series-Parallel Plug-in Hybrid Electric Vehicle
Following the Model-Based-Design (MBD) development process used presently by the automotive industry, the control systems for a new Series-Parallel Multiple-Regime Plug-in Hybrid Electric Vehicle (PHEV), UVic EcoCAR2, have been developed, implemented and tested. Concurrent simulation platforms were …
-
Sport Commitment in Wheelchair Basketball: An Interpretive Look into the Lives of Individuals with Physical Disabilities
… interview method, with the Sport Commitment Model serving as the guiding framework, this study sought to find the underlying factors for continued participation for people with physical disabilities in wheelchair basketball. Through utilizing an interpretive approach it was found that …
-
AUTOMATED AND SECURE SYSTEM FOR MACHINE LEARNING LIFECYCLES
… better predictive performance of downstream models, more efficient transition, more secure remote model serving, etc. Built with the mind of the machine learning pipeline and its evolution, where a pipeline consists of components that flow the raw data to the final model outcome, the system …
-
Rethinking Serverless for Machine Learning Inference
… resource utilization. Specifically, we identify model loading and model memory duplication as major bottlenecks in Serverless Inference, and to address these problems, we propose a new approach that rethinks the way we serve FaaS requests. To support this design, we employ a hybrid scaling …
-
Resource Sharing for Machine Learning Serving
… strides in improving machine learning serving efficiency through various approaches, the rapid evolution of machine learning continues to pose new challenges. Traditional design principles, which focus on optimizing individual components such as computation kernels, memory usage, and …
-
Machine Learning-Based Tire Model Optimization
When developing new vehicles, accurate tire models are crucial for simulating realworld driving behavior. However, inconsistencies in measurement and fitting methods between tire manufacturers introduce bias, leading to different models for the same physical tire. This thesis proposes a method to …
-
Evaluating Incremental Machine Learning Models for Road Condition Classification
… different incremental Machine Learning (ML) models predicting Road Surface Conditions (RSC), using a given data set from Klimator AB. Successfully identifying the RSC is associated with an autonomous vehicle’s traffic safety and therefore an important area of investigation. This project …
-
Research on eeg classification algorithms by sleep stage /
… a deeper 1D ResNet, and a CNN+BiLSTM sequence model implemented in PyTorch. For per-epoch CNNs we apply a five-state Hidden Markov Model (HMM) to the per-epoch logits as temporal post-processing, and enable the same HMM smoothing in the model serving side to maintain parity with evaluation, for …
-
African American Single Mothers' Religiosity and Faith, Suicidal Ideation, and Communication with Their Children
… and perceived severity of the Health Belief Model serving as the foundation for exploring the communication patterns.
-
Heat Exchanger Design for Waste Heat Recovery using Additive Manufacturing
… designs. Consequently, this work centers on the modeling, design, optimization, and testing of AM shell and tube heat exchangers for WHR. Specifically, a modified one-dimensional (1+1-D) and three-dimensional (3-D) heat exchanger models were developed and validated, with the 1+1-D model serving …
-
InferSuite: A Microarchitectural Characterization and System Profiling of LLM Serving and Agentic Inference - CPU/GPU Time and TMA-Style Breakdown Across Serving and Agentic Workloads
… use across retrieval, semantic caching, and model serving. Separately from the service, the same measurement method is applied to two existing agentic workloads, a repository-repair agent and a browser agent, driven through their own unmodified harnesses. Everything runs on one bare-metal …
-
Methodologies and Architectures for AI Inference Hardware: From Foundational Networks to Large Language Models
The rapid advancements in large language models (LLMs) have significantly reshaped the artificial intelligence landscape, enabling transformative applications. However, these developments pose profound challenges for hardware architectures, particularly concerning performance, efficiency, and …
-
Identifying factors associated with bicycle helmet use behavior among college students
… was developed based on the Health Belief Model and the Theory of Reasoned Action, with the Stages of Change Model serving as a tool to classify bicycle riders into groups in accordance with current bicycle helmet use behaviors and future intentions to use. A total of 315 responses were …
-
An empirical investigation of the effects of two goal-setting models on performance and attitudes in a controlled field study
… to investigate the effects of two goal-setting models in a controlled field study. A review of the literature revealed that two different models might be defined as: (1) the ASPIRATIONAL Model and (2) the ASPIRATIONAL + DIRECTIONAL Model. A treatment condition was based on each of the two …
-
Defect Detection for Additive Manufacturing with Machine Learning and Markov Decision Process
… and develop a Markov Decision Process (MDP) model to make decisions for AM process. Our main purpose is to save costs and time through early termination or parameter adjustment of the printing process.</p> <p>In <em>chapter 1</em>, we developed a scheme based on ML models trained. Then these …
Page 1 of 2