CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression

Add code
Oct 10, 2024
Figure 1 for CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
Figure 2 for CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
Figure 3 for CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
Figure 4 for CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: