Zunhai Su

Intermediate
@ZunhaiSu

OScaR-KV-Quant. 🏆 OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond — redefining the accuracy-efficiency Pareto front for X-LLMs KV quantization.

138

Awesome-Attention-Sink. 🚀 First survey on Attention Sink in Transformers — 200+ papers on utilization, interpretation, and mitigation.

137

Super-Experts-Profilling. (ICLR 2026) Unveiling Super Experts in Mixture-of-Experts Large Language Models

43

RotateKV. Code used to reproduce the simulation results of RotateKV.

5

Awesome-Vision-Token-Pruning-for-VLMs.

4

Awesome-Diffusion-Quantization.

1
6
Apply