How can we compress language models without sacrificing accuracy? The number of
compression algorithms for language models is rapidly growing to benefit from remarkable …

Recent advancements in large language models (LLMs) boasting billions of parameters
have generated a significant demand for efficient deployment in inference workloads. While …

Generative Large Language Models (LLMs) based on the Transformer architecture have
recently emerged as a dominant foundation model for a wide range of Natural Language …

Self-attention is an essential component of large language models (LLM) but a significant
source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the …

In this paper, we present a simple optimization-based preprocessing technique called
Weight Magnitude Reduction (MagR) to improve the performance of post-training …

Benefiting from the self-attention mechanism, Transformer models have attained impressive
contextual comprehension capabilities for lengthy texts. The requirements of high …

Modern Machine Learning (ML) models employ sparsity to mitigate storage and computation
costs; but it gives rise to irregular and unstructured sparse matrix operations that dominate …

In real world, large language models (LLMs) can serve as the assistant to help users
accomplish their jobs, and also support the development of advanced applications. For the …

With increasingly more powerful compute capabilities and resources in today's devices,
traditionally compute-intensive automatic speech recognition (ASR) has been moving from …

This is a book about large language models. As indicated by the title, it primarily focuses on
foundational concepts rather than comprehensive coverage of all cutting-edge technologies …