llama.cpp
a81d0c2a
- Fix n^2 loop in tokenization (#254)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
3 years ago
Fix n^2 loop in tokenization (#254) This causes long prompts to parse very slowly.
References
#254 - Fix n^2 loop in tokenization
Author
glinscott
Parents
b2de7f18
Loading