Systems for LLM Inference
- SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning. Lingkun Long, Ruibin Yang, Yushi Huang, Desheng Hui, Ao Zhou, Jianlei Yang, AAAI Conference on Artificial Intelligence (AAAI), 2026.
Zeyu Hao
Master Student
Rubing Yang
Master Student
