neural-nova
/

Llama-3.1-8B-Instruct-optimized

Khanin Udomchoksakul

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

6f657bb verified 4 months ago

127 Bytes

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"]},
	)