Hacker News Reader

If this is "plug and play" can it be added to say llama.cpp and give ~3.67 speedup to existing models or is there some complication?

View on HN

The speedup would not be that high in practice for folks already using speculative decoding[1]. ANPD is similar but uses a simpler and faster drafting approach. These two enhancements can't be meaningfully stacked. Here's how the paper describes it:

> ANPD dynamically generates draft outputs via an adaptive N-gram module using real-time statistics, after which the drafts are verified by the LLM. This characteristic is exactly the difference between ANPD and the previous speculative decoding methods.

ANPD does provide a more general-purpose solution to drafting that does not require training, loading, and running draft LLMs.

[1] https://github.com/ggerganov/llama.cpp/pull/2926

Who is already using speculative decoding? I haven't seen anything about it in the llama.cpp or ollama docs.

https://github.com/ggerganov/llama.cpp/tree/master/examples/...

The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722

I don't think it would be that hard to switch it out for a pretrained ngram model.

Reply on news.ycombinator.com