ChatGLM2-6B icon indicating copy to clipboard operation
ChatGLM2-6B copied to clipboard

Cannot load cpu or cuda kernel, quantization failed:[BUG/Help] <title>

Open Louis24 opened this issue 2 years ago • 0 comments

Is there an existing issue for this?

  • [X] I have searched the existing issues

Current Behavior

Compile default cpu kernel failed. Failed to load kernel. Cannot load cpu or cuda kernel, quantization failed:

Expected Behavior

No response

Steps To Reproduce

import os os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"

os.system("streamlit run web_demo2.py")

Environment

- OS:WIN10
- Python:3.9.12 
- Transformers:4.30.1
- PyTorch:1.12.0+cu113
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :True

Anything else?

No response

Louis24 avatar Jun 28 '23 15:06 Louis24