Releases · jllllll/GPTQ-for-LLaMa-CUDA · GitHub

06 Oct 21:55

0.1.1 Latest

Latest

CUDA 11.7 and ROCm 5.4.2 builds use Pytorch 2.0.1.

All others use Pytorch 2.1.

Assets 38

gptq_for_llama-0.1.1+cu117-cp310-cp310-linux_x86_64.whl

716 KB 2023-10-06T21:57:13Z
gptq_for_llama-0.1.1+cu117-cp310-cp310-win_amd64.whl

752 KB 2023-10-06T21:57:56Z
gptq_for_llama-0.1.1+cu117-cp311-cp311-linux_x86_64.whl

716 KB 2023-10-06T21:55:15Z
gptq_for_llama-0.1.1+cu117-cp311-cp311-win_amd64.whl

752 KB 2023-10-06T21:56:27Z
gptq_for_llama-0.1.1+cu117-cp38-cp38-linux_x86_64.whl

716 KB 2023-10-06T21:55:48Z
gptq_for_llama-0.1.1+cu117-cp38-cp38-win_amd64.whl

752 KB 2023-10-06T21:58:35Z
gptq_for_llama-0.1.1+cu117-cp39-cp39-linux_x86_64.whl

716 KB 2023-10-06T21:55:52Z
gptq_for_llama-0.1.1+cu117-cp39-cp39-win_amd64.whl

752 KB 2023-10-06T22:16:11Z
gptq_for_llama-0.1.1+cu118-cp310-cp310-linux_x86_64.whl

833 KB 2023-10-06T21:58:08Z
gptq_for_llama-0.1.1+cu118-cp310-cp310-win_amd64.whl

861 KB 2023-10-06T22:06:57Z
Source code (zip)

2023-10-06T21:37:15Z
Source code (tar.gz)

2023-10-06T21:37:15Z

09 Aug 18:14

0.1.0

Upload workflows

Assets 38