Microsoft

TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without ...
IEEE

An Innovative Low-Rank Sparse Matrix Decomposition Clutter Suppression Method Based on Non-Convex Alternatives for Pseudo-Random-Coded Ground-Penetrating Radar

Abstract: This article analyzes the composition and characteristics of echo signals in a pseudorandom-coded ground-penetrating radar (GPR). Based on these characteristics, an innovative low-rank ...
IEEE

Optimizing Sparse Matrix-Vector Multiplication on GPUs using the Mathematics of Arrays

Abstract: We present a Mathematics of Arrays (MoA) and ψ-calculus derivation of the memory-optimal operational normal form for ELLPACK sparse matrix-vector multiplication (SpMV) on GPUs. Under the ...