As Large Language Models (LLMs) continue to advance in performance, their size has
escalated significantly, with current LLMs containing billions or even trillions of parameters …

In practice, we usually need to build variable-sized models adapting for diverse resource
constraints in different application scenarios, where weight initialization is an important step …

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-
language-model backbone which suffers from memory bandwidth bottleneck and generates …

Text generation with Large Language Models (LLMs) is known to be memory bound due to
the combination of their auto-regressive nature, huge parameter counts, and limited memory …

Large Language Models (LLMs) are not only resource-intensive to train but even more
costly to deploy in production. Therefore, recent work has attempted to prune blocks of LLMs …

With the rapid growth in the size and complexity of large language models (LLMs), the costs
associated with their training and inference have escalated significantly. Research indicates …

Accurate and efficient flower identification holds significant importance not only for the
general public—who may use this information for educational, recreational, or conservation …