llama.cpp
16090a5d
- parallel : fix sequence termination criteria
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
parallel : fix sequence termination criteria
References
#3228 - llama : custom attention mask + parallel decoding + no context swaps
Author
ggerganov
Parents
806d397c
Loading