KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization

Add code
May 07, 2024
Figure 1 for KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Figure 2 for KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Figure 3 for KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Figure 4 for KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: