Closed sayanmndl21 closed 5 months ago
Just wanted to update: I've figured out the issue was with the Hugging Face embedding, which was initially using the PyTorch ROCm 5.6 backend. Updating to PyTorch ROCm 6.0 fixed the issue. I did note that Torch+ROCm 5.6 works with ROCm 6.0.0 as usual, but the backend for Hugging Face fails so I couldn't bebug the issue properly. This might help others facing similar issues.
@sayanmndl21 , Glad that you have figured it out. I will close this ticket as the issue is outside the scope of rocBLAS. You can re-open the ticket if you need any support from rocBLAS.
Describe the bug
Trying to run any llama_index (0.10.16) RAG tutorial with AMD GPU causes a crash when initializing tensile library. The crash doesn't occur the first time it is being run but any subsequent runs causes this:
While trying to debug I figured out that it might have something to do with vectorstoreindex.
To Reproduce
Install stable rocm (rocm install):
Install llama-index from
pip install llama-index
Reinstall llama-cpp-python with rocm support (might need
sudo -H
):Run tutorial: I am trying this tutorial with local llm: mistral rag tutorial.
Expected behavior
Successfully answer the query.
Log-files
Some lines in the log from debug mode:
Environment
Attached environment.txt
Additional context
Add any other context about the problem here.