neural-nova
/

Llama-3.1-8B-Instruct-optimized

inference-optimization

Model card Files Files and versions

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

378 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

Khanin Udomchoksakul

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

6f657bb verified 6 days ago

__init__.py

781 Bytes
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file 6 days ago
mlp_ext.cpython-312-x86_64-linux-gnu.so

377 kB
xet

Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file 6 days ago