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 10 of 10 for “"LLM Inference"”.

  1. Performance and Energy Efficiency Insights in LLM Inference Across Hardware Accelerators

    The rapid growth of LLM-based applications—such as chatbots, coding assistants, and search engines—has driven the need to deliver LLM inference at scale. This workload is highly resource-demanding, requiring substantial compute throughput along with large, high-bandwidth memory. As a result, …

    uic

  2. Pushing the limits of long context LLM inference via KV cache compression

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for Pushing the limits of long context LLM inference via KV cache compression (opens in a new tab)

  3. The SpaseCroissant Oven: Automatic Metadata Generation For Open-Source Space Weather Datasets

    … a hybrid parsing logic and Large Language Model (LLM) inference approach, as well as recommendations for future Croissant standards and SPASE to Croissant schema metadata conversion, that aims to retain this lost context.

    mit Repository record for The SpaseCroissant Oven: Automatic Metadata Generation For Open-Source Space Weather Datasets (opens in a new tab)

  4. Quantization Methods for Matrix Multiplication and Efficient Transformers

    … products and post-training quantization of LLMs. Beyond reducing the memory footprint, quantization accelerates inference, as the primary bottleneck during autoregressive generation is often the memory bandwidth. NestQuant leverages two nested lattices to construct an efficient vector …

    mit Repository record for Quantization Methods for Matrix Multiplication and Efficient Transformers (opens in a new tab)

  5. Leveraging Large Language Models (LLMs) for Automated Extraction and Processing of Complex Ordering Forms

    … explores the use of Large Language Models (LLMs) to automate the extraction and processing of ordering forms and procurement documents in collaboration with SiliconExperts. These documents contain complex codes used in electronic component procurement, which guide the manufacture and …

    mit Repository record for Leveraging Large Language Models (LLMs) for Automated Extraction and Processing of Complex Ordering Forms (opens in a new tab)

  6. Teaching AIs to Reason and Code, Confidentially

    Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that …

    houston Repository record for Teaching AIs to Reason and Code, Confidentially (opens in a new tab)

  7. Analysis of Memory Access Patterns for Large Language Model Inference

    … deep learning tasks, while only a few focus on inference for large models. The training and inference workloads for the same type of model are quite different: in training, the task is to continuously update the weights matrices with knowledge gained from each training datum, while in inference, …

    vt Repository record for Analysis of Memory Access Patterns for Large Language Model Inference (opens in a new tab)

  8. Monte Carlo Tree Search Applications to Neural Theorem Proving

    A common problem of LLM inference is hallucination, where models generate false information. Another such problem is the tradeoff between model size and computational cost. Larger models use more VRAM, in addition to requiring longer training and inference times. This work explores solutions to …

    mit Repository record for Monte Carlo Tree Search Applications to Neural Theorem Proving (opens in a new tab)

  9. Simulating LLM Runtime Latency

    Large Language Models (LLMs) are expensive to run and can incur high latencies. Each LLM application has its own cost and latency targets. For example, AI voice assistants operate under low latency objectives, while large document batch processing jobs are typically cost-sensitive. However, …

    mit Repository record for Simulating LLM Runtime Latency (opens in a new tab)

  10. Co-Designing Efficient Systems and Algorithms for Sparse and Quantized Deep Learning Computing

    … systems for accelerating large language models (LLMs): TinyChat for edge LLM deployment and QServe for cloud-based LLM serving. TinyChat boosts edge LLM inference by 3× using activation-aware weight quantization (AWQ). QServe further improves performance with activation and KV cache quantization, …

    mit Repository record for Co-Designing Efficient Systems and Algorithms for Sparse and Quantized Deep Learning Computing (opens in a new tab)