加法码本搭配多比特宽度量化方案，为LLM推理加速与压缩提供新思路。
arXiv:2606.12876v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed across heterogeneous hardware with varying…
提出Hyperflux，一种基于L0的新型网络剪枝方法，将剪枝建模为连续演化系统，揭示剪枝过程中神经元重要性变化。
arXiv:2504.05349v4 Announce Type: replace-cross Abstract: Network pruning is used to reduce inference latency and power consumption in large neural ne…
提出专家引导的后合并量化方法，利用合并权重锚定，在低资源部署中平衡模型压缩与性能。
arXiv:2605.16882v1 Announce Type: new Abstract: Low-resource deployment constraints have made model quantization essential for deploying neural networ…