Use the cuda branch of gptq-for-llama

Did I do this right @jllllll? This is because the current default branch (triton) is not compatible with Windows.
This commit is contained in:
oobabooga 2023-03-30 18:04:05 -03:00 committed by GitHub
parent 0de4f24b12
commit 78c0da4a18
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -93,6 +93,7 @@ cd repositories || goto end
if not exist GPTQ-for-LLaMa\ ( if not exist GPTQ-for-LLaMa\ (
git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa.git git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa.git
cd GPTQ-for-LLaMa || goto end cd GPTQ-for-LLaMa || goto end
git checkout cuda
call python -m pip install -r requirements.txt call python -m pip install -r requirements.txt
call python setup_cuda.py install call python setup_cuda.py install
if not exist "%INSTALL_ENV_DIR%\lib\site-packages\quant_cuda-0.0.0-py3.10-win-amd64.egg" ( if not exist "%INSTALL_ENV_DIR%\lib\site-packages\quant_cuda-0.0.0-py3.10-win-amd64.egg" (