search

PromtEngineer / localGPT-Vision

Chat with your documents using Vision Language Models. This repo implements an End to End RAG pipeline with both local and proprietary VLMs
334 stars 65 forks source link

Triton not installed #11

Open eltictacdicta opened 1 week ago

eltictacdicta commented 1 week ago

when I start the application I get this error (my pc is a Ryzen 7 and my graphics card is the GTX 4060): (localgpt-vision) c:\driverslocalGPT-Vision>python app.py WARNING 10-14 20:17:15 _custom_ops.py:18] Failed to import from vllm._C with ModuleNotFoundError(‘No module named “vllm._C”’) INFO 10-14 20:17:16 importing.py:10] Triton not installed; certain GPU-related functions will not be available.

PromtEngineer commented 6 days ago

I think its just a warning. Are you able to run it after the warning?

eltictacdicta commented 3 days ago

Yes, it works but I can't get it to use the GPU for indexing for example, and it only works with GP4o, it doesn't work with any local model.