Friday 31 March 2023

Llama.cpp 30B runs with only 6GB of RAM now

Llama.cpp 30B runs with only 6GB of RAM now
529 by msoad | 148 comments


-
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy 379 by weinzierl | 72 comments