dred0n

exLlama saved GPTQ, I've gone from 6 token/s to over 40, thank you! Currently it's only supports Llama based models. Here's a few other promising architectures such as: MPT Falcon...

Fix Cors issue with files endpoints

2

Issue: The following endpoint used `json.dumps` as a return for the endpoints /refresh-files /select-file This conflicts with FastAPI's ability to assign the proper response headers causing CORS issues. Also, the...