Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference

Add code
Jul 12, 2024
Figure 1 for Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference
Figure 2 for Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference
Figure 3 for Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference
Figure 4 for Multi-Token Joint Speculative Decoding for Accelerating Large Language Model Inference

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: