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 18 of 18 for “"FP16"”.
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… followed by Huffman coding, converting large FP16 tensors into compact bitstreams. Experimental results across three open-source LLMs and six long-context benchmarks from LongBench demonstrate that Quark achieves effective bitwidths of 3.07-3.32 bits, corresponding to compression ratios of …
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… followed by Huffman coding, converting large FP16 tensors into compact bitstreams. Experimental results across three open-source LLMs and six long-context benchmarks from LongBench demonstrate that Quark achieves effective bitwidths of 3.07-3.32 bits, corresponding to compression ratios of …
-
Quantized Lookup Table-Based Representation for Key-Value Cache
… followed by Huffman coding, converting large FP16 tensors into compact bitstreams. Experimental results across three open-source LLMs and six long-context benchmarks from LongBench demonstrate that Quark achieves effective bitwidths of 3.07-3.32 bits, corresponding to compression ratios of …
-
Rychlá předdetekce objektů v obraze
… formátu OpenVINO ve variantách přesnosti FP32, FP16 a INT8 a systematicky testovány na cílovém hardwaru z hlediska rychlosti inference i přesnosti detekce. Na základě výsledků byl jako finální model zvolen YOLOv8n INT8, který dosahuje nejlepšího kompromisu mezi rychlostí a přesností ze všech …
-
ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB
… integer (INT8), half-precision floating-point (FP16), and full-precision floating-point (FP32) inference precision. The improved configuration—partial backbone unfreezing, weighted cross-entropy loss, and extended training—increased ResNet-50 accuracy to 86.8% and EfficientNet-B0 to 81.0%, with …
-
Comparing the Performance of Small Word-Size Floating-Point Numerics to Fixed-Point Numerics in Neural Networks
… floating-point formats (FP8, FP12, FP16) for dynamic, layer-wise quantization during training. APT monitors per-layer Quantization Error Measurement (QEM) to guide precision adjustments and incorporates a novel bit-shuffling mechanism to reallocate bits between exponent and mantissa …
-
Efficient Mixed-Precision Inference for Vision Transformers
… (GB) de memoria en punto flotante de 16 bits (FP16), lo cual requiere múltiples nodos de cómputo acelerado. Esta arquitectura fue transferida a la visión por computadora como Vision Transformer (ViT), donde aumentar el número de parámetros también incrementa el poder predictivo. Versiones …
-
Efficient And Numerically Stable GPU Implementations of The Fast Walsh-Hadamard Transform
… up to 263 and the numerical formats: FP64, FP32, FP16 and BF16. Both implementations suffer heavily from being memory bound, only outperforming Nvidia’s implementation of the computationally heavier Fast Fourier Transform on L4/L40s GPUs when using FP64. We find no benefit of using Alman & Rao’s …
-
Evaluating Design Choices for GPU-Accelerated Finite-Difference Time-Domain Simulation on Resource-Constrained Devices
… for a given computation. Floating point 16 (FP16) is the fastest and most energy-efficient precision choice, but up to 1000 times less accurate. Fixed-point integer formats draw less instantaneous power but run much longer, consuming more total energy, and are tens of thousands of times less …
-
Diseño de una plataforma tecnológica de alto rendimiento con procesamiento por gráfica y basada en tecnología de hiperconvergencia para la aplicación de la inteligencia generativa en el desarrollo de sistemas predictivos de información con el entrenamiento de modelos de Inteligencia Artificial (IA)
… en formato BFLOAT16, 756 TFLOPS en precisión FP16 y 1513 TFLOPS en formato FP8; además, se elevará la velocidad de reloj de los núcleos de cómputo a 1755MHz aprovechando las capacidades del procesamiento en paralelo incorporando la tecnología NVIDIA NVLink; asimismo, se aumentará el número de …
-
OS INSPIRED COMPLETE KERNEL FUSION
… FlashDMoE using FP32 while baselines use FP16.
-
Vision Perception Optimization and Adaptive Control for Resource-Constrained Platform: A Ping-Pong Ball Pickup & Place System
… studies reveal that combining TensorRT with FP16 precision yields a 592.6% performance improvement with negligible accuracy loss. The spiral search strategy demonstrates effective target recovery capabilities when objects temporarily leave the field of view. Most notably, visual servoing …
-
Fast and Energy-Efficient Inference for Attention-Based Natural Language Processing Models
… that focus on the bulk of values to map FP32 or FP16 numbers into 3- or 4-bit indexes to dictionaries of representative values. This means forcing most of the values in a layer to be one of 8 or 16 unique values (instead of 2^32 in single-precision floating-point, FP32, format) while maintaining …
-
Statistical Analysis of Outlier Patterns in Low-bit Quantization Strategies in Large Language Models
… forming a controlled ablation study: FP16 baseline, weight-only rotation (W4A16KV16), W4A4KV4 without prefix, PrefixQuant-O2 ( η1 = 64), and PrefixQuant-EVT ( θEVT = 3.47). Our anal- ysis reveals four key findings. First, Hadamard rotation and prefix isolation address dif- ferent …
-
Mixed-Precision Numerical Linear Algebra Algorithms: Integer Arithmetic Based LU Factorization and Iterative Refinement for Hermitian Eigenvalue Problem
… low-precision formats including half precision (FP16), Bfloat16 and integer operations for quantized integers, which uses integers with a shared scalar to represent a set of equally spaced numbers. As new hardware architectures focus on bringing performance in these formats, the mixed-precision …
-
A Custom RTL Domain-Specific GEMM Accelerator on Cyclone V SoC: Dynamic Precision Selection and Tiling, from RTL Design to Linux Bring-Up for Edge AI Inference and Predictive Control
… the feed path avoids almost all of that cost: BFP16 converts to fixed point before the array, reaches all 64 elements rather than the 16 in the corner, and matches INT16 cycle for cycle to within 0.014%. The conversion costs 514 logic cells, zero DSP slices, and roughly 1% of accelerator power. …
-
Automatic Lyrics Transcription for Greek Songs
… Transformers, batch size 4-8, μικτή ακρίβεια FP16 και optimizer AdamW (learning rate 5×10⁻⁵). Η αξιολόγηση της απόδοσης βασίστηκε στη μετρική normalized Word Error Rate (WER), η οποία εξουδετερώνει την επίδραση της στίξης και των μικρο-ορθογραφικών διαφορών. Πειραματικά, το zero-shot …
-
Evidence for the utility of the script concept as a model for children's friendship formation
Thesis (Ph. D.)--Michigan State University. Department of Psychology, 1984