llama.cpp
f6e1a7aa
- context : simplify output counting logic during decode (#14142)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
87 days ago
context : simplify output counting logic during decode (#14142) * batch : remove logits_all flag ggml-ci * context : simplify output counting logic during decode ggml-ci * cont : fix comments
References
#14142 - context : simplify output counting logic during decode
Author
ggerganov
Parents
c3ee46fa
Loading