Juan Fran comments

Repositories
Issues
Comments

Results 2 comments of


                                            Juan Fran

Errors loading models cublas

Until it is fixed, I recommend using this docker image which has inside go-llama.cpp quay.io/go-skynet/local-ai:sha-49a2b30-cublas-cuda12 It is an older one (a few days ago) but functional with models like q4_0

[PR] Added Docker Example Usage / Support - Still needs support for multiple concurrent instances

Thank you, but I didn't ask to be merged as I'm in a WIP state with this. Once it is completed I will have a complete standalone version running in...