Raven Scott

`$ dat-doctor Welcome to Dat Doctor! Software Info: linux x64 Node v10.19.0 Dat Doctor v2.1.2 Running Basic Tests (Checks your Dat installation and network setup) ✖ Who am I? ERROR:...

https://github.com/ggerganov/llama.cpp/pull/1105 This may be relevant

The above was merged, we should be able to set cache as needed

Relevant issue has been opened by another dev over at llama.cpp: https://github.com/ggerganov/llama.cpp/issues/1054

Furthermore, this issue has been reopened so it may be fixed within llama.cpp: https://github.com/ggerganov/llama.cpp/issues/730 If you would like we can close this issue since there obviously is a solution coming.

Closing this in favor of #44

@Konata390 Thank you for the wonderful idea! I have created #136 to complete this request.

Are you able to grab the containers log so we can see what the issue may be? Best way is to use `docker logs containerName` since portainer will turn most...

AVX1 is actually supported in llama.cpp within recent merges see: https://github.com/ggerganov/llama.cpp/commit/02c5b27e91a6d18cf1043d3a2d8dbc59610ac257 Was your issue with AVX1 compatibility or just AVX in general? AVX1 or AVX2 would be a llama.cpp requirement,...

If it works it works :) Hopefully the slowness can be worked out in llama.cpp someday. Celeron is a good point!