Inferinite.AI

AI & ML interests

None defined yet.

Recent Activity

zhiqix  authored a paper about 24 hours ago

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

zheweiyao  authored a paper over 1 year ago

SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation

zheweiyao  authored a paper over 2 years ago

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design

View all activity

Team members 5