Chun Jason Xue
2024
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
Junhui He
|
Shangyu Wu
|
Weidong Wen
|
Chun Jason Xue
|
Qingan Li
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
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.
When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models
Weilan Wang
|
Yu Mao
|
Tang Dongdong
|
Du Hongchao
|
Nan Guan
|
Chun Jason Xue
Findings of the Association for Computational Linguistics: EMNLP 2024
Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a framework to compress LLM after quantization further, achieving about 2.2x compression ratio. A compression-aware quantization is first proposed to enhance model weight compressibility by re-scaling the model parameters before quantization, followed by a pruning method to improve further. Upon this, we notice that decompression can be a bottleneck during practical scenarios. We then give a detailed analysis of the trade-off between memory usage and latency brought by the proposed method. A speed-adaptive method is proposed to overcome it. The experimental results show inference with the compressed model can achieve a 40% reduction in memory size with negligible loss in accuracy and inference speed.
Search
Co-authors
- Junhui He 1
- Shangyu Wu 1
- Weidong Wen 1
- Qingan Li 1
- Weilan Wang 1
- show all...