2025 "post-training compression" Papers
2 papers found
DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
Hanling Zhang, Rundong Su, Zhihang Yuan et al.
ICCV 2025posterarXiv:2503.22796
10
citations
Palu: KV-Cache Compression with Low-Rank Projection
Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin et al.
ICLR 2025poster
16
citations