Jun Yao


2024

pdf bib
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
Ruikang Liu | Haoli Bai | Haokun Lin | Yuening Li | Han Gao | Zhengzhuo Xu | Lu Hou | Jun Yao | Chun Yuan
Findings of the Association for Computational Linguistics ACL 2024

Large language models (LLMs) excel in natural language processing but demand intensive computation. To mitigate this, various quantization methods have been explored, yet they compromise LLM performance. This paper unveils a previously overlooked type of outliers in LLMs. Such outliers are found to allocate most of the attention scores on initial tokens of input, termed as pivot tokens, which are crucial to the performance of quantized LLMs. Given that, we propose IntactKV to generate the KV cache of pivot tokens losslessly from the full-precision model. The approach is simple and easy to combine with existing quantization solutions with no extra inference overhead. Besides, IntactKV can be calibrated as additional LLM parameters to boost the quantized LLMs further with minimal training costs. Mathematical analysis also proves that IntactKV effectively reduces the upper bound of quantization error. Empirical results show that IntactKV brings consistent improvement over various quantization methods across different LLMs and downstream tasks, leading to the new state-of-the-art for LLM quantization. The codes are available at https://github.com/ruikangliu/IntactKV.

2021

pdf bib
HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task
Hengchao Shang | Ting Hu | Daimeng Wei | Zongyao Li | Jianfei Feng | ZhengZhe Yu | Jiaxin Guo | Shaojun Li | Lizhi Lei | ShiMin Tao | Hao Yang | Jun Yao | Ying Qin
Proceedings of the Sixth Conference on Machine Translation

This paper presents the submission of Huawei Translation Services Center (HW-TSC) to WMT 2021 Efficiency Shared Task. We explore the sentence-level teacher-student distillation technique and train several small-size models that find a balance between efficiency and quality. Our models feature deep encoder, shallow decoder and light-weight RNN with SSRU layer. We use Huawei Noah’s Bolt, an efficient and light-weight library for on-device inference. Leveraging INT8 quantization, self-defined General Matrix Multiplication (GEMM) operator, shortlist, greedy search and caching, we submit four small-size and efficient translation models with high translation quality for the one CPU core latency track.