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 8 of 8 for “"energy-efficient inference"”.
-
Cross-layer methods for energy-efficient inference using in-memory architectures
… such as DNNs under stringent constraints on energy, latency, and form-factor is a formidable challenge. In conventional von Neumann architectures, the energy and latency cost of realizing ML algorithms is dominated by memory accesses. To address this issue, the deep in-memory architecture …
-
Fast and Energy-Efficient Inference for Attention-Based Natural Language Processing Models
… This thesis' goal is to reduce the cost of inference for Transformer models in terms of latency and energy consumption to help enabling widespread application in our daily lives. Since in these models, the primary performance and energy efficiency bottleneck is memory transactions, this …
-
Hardware/Neural Network Codesign for Energy-Efficient Inference on Edge Devices with Optimal Mapping and Compression
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Efficient Real-Time Localization Systems: Measurements, Algorithms, and Hardware
… such as limited computational resources, energy consumption, and real-time processing requirements. As a result, localization should be viewed not only as an estimation problem but also as a broader system design problem that involves measurements from sensors, algorithm selection, and …
-
LLM-Guided Run-Time Parameter Optimization for Energy-Efficient Model Inference
… However, LLMs consume a tremendous amount of energy, which becomes a large concern in the scale of the demand for these tools. Inference engines and serving systems, like vLLM and PyTorch, are used to perform efficient LLM inference. These tools include runtime parameters that have the …
-
Scalable and Versatile Hardware Acceleration of Graph Neural Networks
… e-commerce) that use graph models. However, efficient GNN acceleration faces with multiple challenges related to high and variable sparsity of input feature vectors, power-law degree distribution in the adjacency matrix, and maintaining load-balanced computation with minimal random memory …
-
Efficient inference and adaptation in deep learning : from edge systems to large language models
… constraints, including latency, memory, and energy limitations. Consequently, improving the resource efficiency of DL throughout its lifecycle has become an increasingly important research problem.This thesis investigates efficient inference, training, and adaptation in DL across the model …
-
Automatizovaný návrh aproximativních architektur konvolučních neuronových sítí pro energeticky úspornou inferenci
… modelu zohledňují energetickou náročnost inference na cílové hardwarové platformě. Aproximační výpočty, založené na záměrném uvolnění aritmetické přesnosti, představují účinný prostředek ke snížení energetické náročnosti inference. Jejich systematická integrace do automatizovaného návrhu …