Follow
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models. (arXiv:2206.09557v3 [cs.DC] UPDATED)
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models. (arXiv:2206.09557v3 [cs.DC] UPDATED)