In this paper, we present CORING, which is short for effiCient tensOr decomposition-based
filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to …

With the rapid growth of large language models (LLMs), there is increasing demand for
memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to …

In this paper, we present DSA, the first automated framework for discovering sparsity
allocation schemes for layer-wise pruning in Large Language Models (LLMs). LLMs have …

Large language models (LLMs) have demonstrated outstanding performance in various
tasks, such as text summarization, text question-answering, and etc. While their performance …

Large Language Models (LLMs) are distinguished by their massive parameter counts, which
typically result in significant redundancy. This work introduces MaskLLM, a learnable …

Most existing neural network pruning methods hand-crafted their importance criteria and
structures to prune. This constructs heavy and unintended dependencies on heuristics and …

Deep neural networks (DNNs) have recently achieved impressive success across a wide
range of real-world vision and language processing tasks, spanning from image …

Network pruning has attracted increasing attention recently for its capability of transferring
large-scale neural networks (eg, CNNs) into resource-constrained devices. Such a transfer …

Abstract Large Language Models (LLMs) have revolutionized the field of natural language
processing with their impressive capabilities. However, their enormous size presents …

N: M sparsity is an emerging model compression method supported by more and more
accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing …