Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models

arXiv:2404.11502v1 Announce Type: new
Abstract: 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 wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods …

abstract advanced application applications arxiv assistant cs.ai cs.cl development efficiency evaluation inference jobs language language models large language large language models llms serve support type world