llama.cpp
2f3a46fc
- train : make KQ_pos memory buffer permanent via dummy scale op
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
train : make KQ_pos memory buffer permanent via dummy scale op
References
#3228 - llama : custom attention mask + parallel decoding + no context swaps
Author
ggerganov
Parents
54206962
Loading