3 papers
cs.AR2026
Fast Cross-Operator Optimization of Attention Dataflow
Haodong Chang, Hailiang Hu, Zhenrui Wang +5
Attention is a fundamental computational kernel that accounts for the majority of the workload in transformer and LLM computing. Optimizing dataflow is crucial for enhancing both p…
cs.CV2025
TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
Cheng Yang, Yang Sui, Jinqi Xiao +8
Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Pre…
cs.LG2024
MoE-I: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
Cheng Yang, Yang Sui, Jinqi Xiao +7
The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by…