B. Lipshitz
YOU?
Author Swipe
View article: Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon
Accelerating Sparse Ternary GEMM for Quantized ML on Apple Silicon Open
Sparse Ternary General Matrix-Matrix Multiplication (GEMM) remains under-optimized in existing libraries for Apple Silicon CPUs. We present a Sparse Ternary GEMM kernel optimized specifically for Apple's M-series processors. We propose a s…