Rethinking Cross-Layer Information Routing in Diffusion Transformers Paper • 2605.20708 • Published 29 days ago • 110
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps Paper • 2605.16928 • Published May 16 • 95
Inference Performance Optimization for Large Language Models on CPUs Paper • 2407.07304 • Published Jul 10, 2024 • 53