SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
| Title: | SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs |
|---|---|
| Authors: | Xu, Jiaming; Pan, Jiayi; Wang, Hanzhen; Zhou, Yongkang; Ye, Jiancai; Wang, Yu; Dai, Guohao |
| Source: | Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2. :1832-1847 |
| Availability: | http://dl.acm.org/doi/10.1145/3779212.3790224 |
| Database: | ACM Full-Text Collection |