Han Bao

Researcher, Huawei Technologies Ltd.

Joined

May 2024

Names

Han Bao (Preferred)

Emails

****@huawei.com (Confirmed)

Personal Links

Google Scholar

ORCID

Career & Education History

Researcher

Huawei Technologies Ltd. (huawei.com)

2023 – Present

MS student

, Chinese Academy of Sciences (ict.ac.cn)

2020 – 2023

Undergrad student

Nankai University (nku.nankai.edu.cn)

2016 – 2020

Advisors, Relations & Conflicts

Coauthor

Weile Jia

2020 – 2023

Expertise

High Performance Computing

2020 – Present

Publications

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
- ACL 2026 Industry Track Oral
- Readers: Everyone
BoundaryDPT: Pushing the Boundaries of Depth Pruning for Vision Transformers
Zhenfeng Su, Kang Zhao, Han Bao, Tao Yuan, Xianzhi Yu
- Submitted to ICLR 2026
- Readers: Everyone
FlatQuant: Flatness Matters for LLM Quantization
Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang Zhao, Yuening Li, JiaxinHu, Xianzhi Yu, Lu Hou, Chun Yuan, Xin Jiang, Wulong Liu, Jun Yao
- ICML 2025 poster
- Readers: Everyone
Beyond 2:4: Exploring V:N:M Sparsity for Efficient Transformer Inference on GPUs
Kang Zhao, Tao Yuan, Han Bao, Zhenfeng Su, Chang Gao, Zhaofeng Sun, Zichen Liang, Liping Jing, Jianfei Chen
- Submitted to ICLR 2025
- Readers: Everyone
FlatQuant: Flatness Matters for LLM Quantization
Yuxuan Sun, Ruikang Liu, Haoli Bai, Han Bao, Kang Zhao, Yuening Li, JiaxinHu, Xianzhi Yu, Lu Hou, Chun Yuan, Xin Jiang, Wulong Liu, Jun Yao
- Submitted to ICLR 2025
- Readers: Everyone
FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs for Efficient Inference
Haoran Lin, Xianzhi Yu, Kang Zhao, Lu Hou, ZongYuan Zhan, Stanislav Kamenev, Han Bao, Ting Hu, Mingkai Wang, QixinChang, Siyue Sui, Weihao sun, JiaxinHu, Jun Yao, Zekun Yin, Cheng Qian, Ying Zhang, PanYinfei, Yang yu, Weiguo Liu
- Submitted to ICLR 2025
- Readers: Everyone

Co-Authors

View all 42 co-authors

Han Bao

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats

BoundaryDPT: Pushing the Boundaries of Depth Pruning for Vision Transformers

FlatQuant: Flatness Matters for LLM Quantization

Beyond 2:4: Exploring V:N:M Sparsity for Efficient Transformer Inference on GPUs

FlatQuant: Flatness Matters for LLM Quantization

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs for Efficient Inference

Co-Authors