Tao Wei

Research progress on vascular access information system both here and abroad

2018 · Zhonghua xiandai huli zazhi

This paper reviewed the research progress on vascular access information system from two aspects including development and advantages of vascular access information system both here and abroad. This paper focused on expounding the achieving functions …

Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference

2025 · arXiv (Cornell University)

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision quantization …