Download LLM-Drop/src/llmtuner/compression/quantization/AutoGPTQ/setup_cuda.py from s1ghhh/nbl_try: direct link, hf CLI and curl.
- Browser
- Download file 287 Bytes
-
https://huggingface.co/s1ghhh/nbl_try/resolve/main/LLM-Drop/src/llmtuner/compression/quantization/AutoGPTQ/setup_cuda.py
- Command line
-
hf download hf://s1ghhh/nbl_try/LLM-Drop/src/llmtuner/compression/quantization/AutoGPTQ/setup_cuda.py
-
curl -L -o setup_cuda.py https://huggingface.co/s1ghhh/nbl_try/resolve/main/LLM-Drop/src/llmtuner/compression/quantization/AutoGPTQ/setup_cuda.py
287 Bytes
| from setuptools import setup, Extension | |
| from torch.utils import cpp_extension | |
| setup( | |
| name='quant_cuda', | |
| ext_modules=[cpp_extension.CUDAExtension( | |
| 'quant_cuda', ['quant_cuda.cpp', 'quant_cuda_kernel.cu'] | |
| )], | |
| cmdclass={'build_ext': cpp_extension.BuildExtension} | |
| ) | |