FasterDecoding

AI & ML interests

Making model inference more efficient by model-system codesign.

Recent Activity

Gsunshine  authored a paper about 19 hours ago

Representation Fréchet Loss for Visual Generation

tianlecai  authored a paper 9 months ago

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

tianlecai  authored a paper about 2 years ago

SnapKV: LLM Knows What You are Looking for Before Generation

View all activity

Team members 3