Cite
Notes
Only stored in your browser.
Attribution
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation
arXiv 2025
TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
arXiv 2024
from 3 papers
Muhan Zhang
Fan Jiang
Fanxu Meng
Di Yin
Fauxu meng
Xiaojuan Tang
Xing Sun
Xuefeng Zhang
Yiding Wang
Yuxuan Wang