@misc{wang2024bitnet,
author = {Wang, Hongyu and Ma, Shuming and Wei, Furu},
title = {BitNet a4.8: 4-bit Activations for 1-bit LLMs},
howpublished = {arXiv},
year = {2024},
month = {November},
abstract = {Recent research on the 1-bit Large Language Models (LLMs), such as BitNet b1.58, presents a promising direction for reducing the inference cost of LLMs while maintaining their performance. In this work, we introduce BitNet a4.8, enabling 4-bit activations for 1-bit LLMs. BitNet a4.8 employs a hybrid quantization and sparsification strategy to mitigate the quantization errors introduced by the outlier channels. Specifically, we utilize 4-bit activations for inputs to the attention and feed-forward network layers, while sparsifying intermediate states followed with 8-bit quantization. Extensive experiments demonstrate that BitNet a4.8 achieves performance comparable to BitNet b1.58 with equivalent training costs, while being faster in inference with enabling 4-bit (INT4/FP4) kernels. Additionally, BitNet a4.8 activates only 55% of parameters and supports 3-bit KV cache, further enhancing the efficiency of large-scale LLM deployment and inference.},
url = {http://approjects.co.za/?big=en-us/research/publication/bitnet-a4-8-4-bit-activations-for-1-bit-llms/},
note = {Work in progress},
}