neural-nova
/

Llama-3.1-8B-Instruct-optimized

inference-optimization

Model card Files Files and versions

Llama-3.1-8B-Instruct-optimized / kernels

Commit History

Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file

6f657bb
verified

Khanin Udomchoksakul commited on 4 days ago