llama.cpp
003c9035
- ngram-map : take into account the input can become shorter
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 day ago
ngram-map : take into account the input can become shorter
References
#18471 - Add self‑speculative decoding (no draft model required)
Author
ggerganov
Parents
9f8401a5
Loading