Zoli Somogyi

Test failed: It runs on my computer, I do not see any problem (nothing important has changed compared to before when all tests were OK). Try to restart the test....

> I've restarted the tests, but I'm not expecting them to pass right now. We seem to have an issue with one specific test at the moment that consistently fails...

I have corrected several problems in the code and I could make all tests pass (in the macOSX tests with skipping only 1). One of the problems I have corrected...

> Could you split the csproj file downloading changes to a separate PR? The `SkipUnchangedFiles="true"` attribute should prevent duplicate downloads, so we'll want to look into that. Having it all...

> Sorry for the delay on this, I'd hoped to get the binary update PR in first but that's taking a long time! Thank you Martin! Yes, I was expecting...

Thank you, Martin. I am a bit hesitant because I’m confused about how [ggerganov](https://github.com/ggerganov) still manages to maintain the former file sizes (~60 MB for the DLL), while we are...

I believe I've identified the issue. I now have a smaller ggml-cuda.dll (51MB for the Windows Release with one architecture and 157MB with two architectures). The issue seems to stem...

> > They are in that build, search for "MB" and that'll highlight the relevant items: > > ``` > ggml-cuda-bin-linux-cublas-cu11.7.1-x64.so : 175MB > ggml-cuda-bin-linux-cublas-cu12.8.0-x64.so : 113MB > ggml-cuda-bin-win-cublas-cu11.7.1-x64.dll :...

**IMPORTANT NEWS**: The last master from llama.cpp corrects the BUG with the DLL sizes and also the CUDA graphs problem (https://github.com/ggml-org/llama.cpp/issues/12152) that was causing regular crashes in LLamaSharp. Unfortunately 'llama_model_params'...

Try to set the Embeddings parameter in ModelParams to true.