Skip to content
Discussion options

You must be logged in to vote

👋 jlama-native is not required. It’s an alternative implementation on tensor operation that use native simd. The reason for this is the Java vector api is still not perfect and more complex vector dense methods like quantized GEMM can be de-optimized at runtime.

So YMMV and native helps normalize performance if needed.

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by isaaca26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants