Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Speculative decoding (SD) accelerates large language model inference by employing a
faster draft model for generating multiple tokens, which are then verified in parallel by the …

Large Language Models (LLMs) have showcased exceptional capabilities in various
domains, attracting significant interest from both academia and industry. Despite their …

Transformer based large language models have achieved tremendous success. However,
the significant memory and computational costs incurred during the inference process make …

Recent advancements in large language models (LLMs) have raised concerns about
inference costs, increasing the need for research into model compression. While knowledge …

Despite the success of Large Language Models (LLMs), they still face challenges related to
high inference costs and memory requirements. To address these issues, Knowledge …

Advanced Large language models (LLMs) like GPT-4 or LlaMa 3 provide superior
performance in complex human-like interactions. But they are costly, or too large for edge …

As Generative AI becomes more prevalent, the vulnerability to security threats grows. This
study conducts a thorough exploration of red teaming methods within the domain of …

Recently, considerable efforts have been directed towards compressing Large Language
Models (LLMs), which showcase groundbreaking capabilities across diverse applications …

Transferring the reasoning capability from stronger large language models (LLMs) to smaller
ones has been quite appealing, as smaller LLMs are more flexible to deploy with less …