Khanin Udomchoksakul
Add optimized CUDA kernels (RMSNorm, MLP, Attention) and patched Llama-3.1 modeling file
6f657bb verified | from setuptools import setup | |
| setup( | |
| name="mlp_ext", | |
| packages=["mlp_cuda"], | |
| package_data={"mlp_cuda": ["*.so"]}, | |
| ) | |
| from setuptools import setup | |
| setup( | |
| name="mlp_ext", | |
| packages=["mlp_cuda"], | |
| package_data={"mlp_cuda": ["*.so"]}, | |
| ) | |