In this post, we explain how P-EAGLE works, how we integrated it into vLLM starting from v0.16.0 (PR#32887), and how to serve it with our pre-trained checkpoints.
EAGLE is the state-of-the-art method for speculative decoding in large language model (LLM) inference, but its autoregressive drafting creates a hidden bottleneck: the more tokens that you speculate,… [+17892 chars]
