Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMs
Tao Ji, Bin Guo, Yuanbin Wu, Qipeng Guo, Shenlixing Shenlixing, Chenzhan Chenzhan, Xipeng Qiu, Qi Zhang, Tao Gui. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
Authors
- Qi Zhang (ORCID: https://orcid.org/0000-0002-5203-8778)
- Qipeng Guo (ORCID: https://orcid.org/0000-0001-7113-651X)
- Xipeng Qiu (ORCID: https://orcid.org/0000-0001-7163-5247)
- Tao Gui (ORCID: https://orcid.org/0000-0002-6154-0751)
- Bin Guo (ORCID: https://orcid.org/0000-0001-6097-2467)
- Tao Ji (ORCID: https://orcid.org/0000-0002-7671-5921)
- Yuanbin Wu (ORCID: https://orcid.org/0000-0002-4665-6350)
- Shenlixing Shenlixing
- Chenzhan Chenzhan
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.1597
- Citations
- 2
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Natural Science Foundation of Shanghai
- National Natural Science Foundation of China
- Fudan University
- Shanghai Rising-Star Program
- Program of Shanghai Academic Research Leader