1 unstable release

0.1.1 Jul 25, 2023
0.1.0 Jul 25, 2023

#673 in Machine learning

MIT license

20KB
415 lines

llama2 in Rust!

This was derived from https://github.com/karpathy/llama2.c to run multi-threaded inference.

It's 3+ times faster to run inference using this Rust port than the original llama2.c.

Dependencies

~5MB
~100K SLoC