Optimized Inference for 1.58-bit LLMs: A Time and Memory-Efficient Algorithm for Binary and Ternary Matrix Multiplication

Add code
Nov 10, 2024
Figure 1 for Optimized Inference for 1.58-bit LLMs: A Time and Memory-Efficient Algorithm for Binary and Ternary Matrix Multiplication
Figure 2 for Optimized Inference for 1.58-bit LLMs: A Time and Memory-Efficient Algorithm for Binary and Ternary Matrix Multiplication
Figure 3 for Optimized Inference for 1.58-bit LLMs: A Time and Memory-Efficient Algorithm for Binary and Ternary Matrix Multiplication
Figure 4 for Optimized Inference for 1.58-bit LLMs: A Time and Memory-Efficient Algorithm for Binary and Ternary Matrix Multiplication

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: