FasterDecoding

AI & ML interests

Making model inference more efficient by model-system codesign.

Recent Activity

tianlecai  authored a paper 12 days ago

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

tianlecai  authored a paper over 1 year ago

SnapKV: LLM Knows What You are Looking for Before Generation

tianlecai  authored a paper over 1 year ago

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

View all activity

Team members 3