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 7 of 7 for “"INT8 quantization"”.

  1. Language Model Inference on FPGA with Integer-only Operations

    … models for the GLUE benchmark tasks with INT8 quantization. These findings reveal that integer-only transformer inference on FPGAs is a feasible way of implementing complex language models on resource-limited edge devices, with the potential for new privacy-conscious, low-latency AI …

    waterloo Repository record for Language Model Inference on FPGA with Integer-only Operations (opens in a new tab)

  2. ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB

    … configurations corresponding to 8-bit 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 …

    nps Repository record for ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB (opens in a new tab)

  3. Anomaly Detection on Power Input Using Machine Learning on Microcontroller Systems

    … the same 20 ms context. After full-integer (INT8) quantization, the 1D-CNN preserves accuracy while reducing the model size to about 21 kB and achieving ≈ 0.03 ms inference per 20 ms window, meeting real-time MCU constraints. In contrast, the recurrent models require SELECT_TF_OPS support in …

    chalmers Repository record for Anomaly Detection on Power Input Using Machine Learning on Microcontroller Systems (opens in a new tab)

  4. An Edge AI Test Bench for Unsupervised Anomaly Detection

    … classification scores. Third, post-training INT8 quantization collapses MOMENT’s accuracy to chance when applied naively; restricting INT8 to the FFN linears preserves FP32 accuracy at all three model sizes with a 1.33–1.82× disk reduction and 1.25–1.55× latency reduction, and the small and …

    chalmers Repository record for An Edge AI Test Bench for Unsupervised Anomaly Detection (opens in a new tab)

  5. Accessible Foundation Models: Systems, Algorithms, and Science

    … scratch. For inference, I will describe our LLM.int8() algorithm, which showed how to enable high-precision 8-bit matrix multiplication that is both fast and memory efficient. LLM.int8() is based on the discovery and characterization of sparse outlier sub-networks that only emerge at large model …

    washington Repository record for Accessible Foundation Models: Systems, Algorithms, and Science (opens in a new tab)

  6. Application of Large Language Models in Code Clone: Benchmarking, Evaluation and Detection

    … model using knowledge distillation (KD) and INT8 quantization-aware training (QAT). Our approach compressed LLM model, significantly reducing the number of attention heads, hidden dimensions, and layers while maintaining high performance. To compare with the existing LLM-tools which were …

    sask Repository record for Application of Large Language Models in Code Clone: Benchmarking, Evaluation and Detection (opens in a new tab)

  7. Integer Quantization and Embedded Deployment of CNN Star Trackers for CubeSats

    A star tracker determines spacecraft orientation by photographing the star field, detecting stars in the image, matching them against a catalog, and computing the rotation between observed and cataloged directions. Convolutional neural networks (CNNs) have been proposed as replacements for the …

    calpoly Repository record for Integer Quantization and Embedded Deployment of CNN Star Trackers for CubeSats (opens in a new tab)