Deming Chen
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
arXiv 2024
SnapKV: LLM Knows What You are Looking for Before Generation
arXiv 2024
What Makes Convolutional Models Great on Long Sequence Modeling?
arXiv 2022
Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture
arXiv 2021
Affiliations
No known affiliations.
Frequent co-authors
10from 4 papers