Accueil Explorer Aide
Connexion
cturan
/
llama.cpp
miroir de https://github.com/cturan/llama.cpp
1
0
Fork 0
Fichiers Tickets 0 Wiki
Branche: qwen3_next_optimized
Branches Tags
llama.cpp
/
examples
/
lookup
Georgi Gerganov 254098a279 common : refactor common_sampler + grammar logic changes (#17937) il y a 1 mois
..
CMakeLists.txt 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) il y a 1 an
README.md 68ff663a04 repo : update links to new url (#11886) il y a 11 mois
lookup-create.cpp 254098a279 common : refactor common_sampler + grammar logic changes (#17937) il y a 1 mois
lookup-merge.cpp 7eee341bee common : use common_ prefix for common library functions (#9805) il y a 1 an
lookup-stats.cpp 254098a279 common : refactor common_sampler + grammar logic changes (#17937) il y a 1 mois
lookup.cpp 254098a279 common : refactor common_sampler + grammar logic changes (#17937) il y a 1 mois

README.md

llama.cpp/examples/lookup

Demonstration of Prompt Lookup Decoding

https://github.com/apoorvumang/prompt-lookup-decoding

The 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.

More info:

https://github.com/ggml-org/llama.cpp/pull/4484 https://github.com/ggml-org/llama.cpp/issues/4226