uniql-quantization-pruning

【效率与协作】Single cloud-side weight-sorting and fine-tuning supporting multiple on-device pruning rates via efficient SVD and MLP decomposition, achieving 4-5.7× memory reduction and 2.7-3.4× throughput across Transformers, SSMs, and hybrid architectures.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准