Saved in:
Bibliographic Details
Main Authors: He, Junhui, Wu, Shangyu, Wen, Weidong, Xue, Chun Jason, Li, Qingan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.01366
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915079973240832
author He, Junhui
Wu, Shangyu
Wen, Weidong
Xue, Chun Jason
Li, Qingan
author_facet He, Junhui
Wu, Shangyu
Wen, Weidong
Xue, Chun Jason
Li, Qingan
contents Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation sparsification problem to explicitly capture the relationship between activation sparsity and model performance. Then, this paper proposes CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over eight downstream tasks while activating fewer parameters than existing methods, thus speeding up the LLM inference by up to 1.27x.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01366
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
He, Junhui
Wu, Shangyu
Wen, Weidong
Xue, Chun Jason
Li, Qingan
Computation and Language
Artificial Intelligence
Machine Learning
Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation sparsification problem to explicitly capture the relationship between activation sparsity and model performance. Then, this paper proposes CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over eight downstream tasks while activating fewer parameters than existing methods, thus speeding up the LLM inference by up to 1.27x.
title CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2409.01366