大模型压缩新招：SVD奇异值手术实现最优精度-效率平衡，部署优化必读
arXiv:2606.23568v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their de…
提出跨层KV-Cache压缩新方法xKV，利用对齐奇异向量提取大幅减少显存占用，加速大模型推理。
arXiv:2503.18893v2 Announce Type: replace-cross Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory…
MuCon通过裁剪奇异值改进Muon优化器，为LLM训练提供更稳定的更新策略
arXiv:2605.26459v1 Announce Type: new Abstract: Muon-style optimizers take a matrix-valued momentum or preconditioned update $B = U \operatorname{diag…