2 papers
cs.DC2026
MpFA: Hardware-Efficient Train-Free QK4V8 FlashAttention Kernels on Blackwell GPUs
Chencheng Deng, Jianbin Fang, Dezun Dong
Long-context LLM inference pushes modern GPU serving stacks into an attention-bound regime, where both compute and memory are dominated by the softmax-GEMM pipeline. On NVIDIA Blac…
cs.DC2025
Demystifying ARM SME to Optimize General Matrix Multiplications
Chencheng Deng, Weiling Yang, Jianbin Fang +1
General Matrix Multiplication (GEMM) is a critical kernel in high-performance computing and deep learning. While modern architectures like ARM's Scalable Matrix Extension (SME) int…