Zoli Somogyi

Thank you for your answer! - I used what was required: 'sw setup' - I have changed the storage dir in sw.yml to an other drive but you can not...

1. After setup I have: - storage\pkg -> 182 folders with at least 20 subfolders per folder (called '00', '0b', '0d', ...). That is at least 4000 folders with many...

Thank you for your answer! I do not agree because I use 10-12 software packages and not hundreds of them! I find this a bug (or design fault) in your...

Please find my input here under: 1. I would completely rework the look and feel. I would choose something similar to this [https://github.com/mlpack/mlpack/wiki/UsingCMake](https://github.com/mlpack/mlpack/wiki/UsingCMake). It should be easy to read, easy...

This PR causes crash in the pooling code (cuMemUnmap). I have corrected the code and streamlined it for llama.cpp: https://github.com/ggerganov/llama.cpp/pull/5898

I am a bit confused. I thought that @slaren solved this problem with 'llama : add pipeline parallelism support (https://github.com/ggerganov/llama.cpp/pull/6017)'? Or do you mean here something else? @slaren said that...

I understand. Thank you that you care about this issue and that you will work on it! I have tried to solve it but I could not.

Some additional problems https://github.com/ggerganov/llama.cpp/issues/6909 maybe because of this fix?

https://github.com/SciSharp/LLamaSharp/commit/c325ac91279428e8d88719357b93e43cd9c5ed52#commitcomment-141108660

First of all, we definitely need embedding generation with normal/generative models! I can also confirm that the old code was not broken and worked well for me with normal/generative models....