most citedInfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2024★ 1 cited

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

Wonbeom Lee, Jungi Lee, Junghwan Seo +1

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long conten…