SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Add code
Oct 09, 2024
Figure 1 for SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Figure 2 for SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Figure 3 for SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Figure 4 for SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: