1# llama.cpp/examples/lookup
2
3Demonstration of Prompt Lookup Decoding
4
5https://github.com/apoorvumang/prompt-lookup-decoding
6
7The key parameters for lookup decoding are `ngram_min`, `ngram_max` and `n_draft`. The first two determine the size of the ngrams to search for in the prompt for a match. The latter specifies how many subsequent tokens to draft if a match is found.
8
9More info:
10
11https://github.com/ggml-org/llama.cpp/pull/4484
12https://github.com/ggml-org/llama.cpp/issues/4226