Phylliida Dev

Hey! Thanks for the suggestion. I actually really like Spitfire and wrote a (almost) working wrapper into this project and in Unity a bit ago, it’s a great project. However,...

Hmm I went back again to go check and noticed my Spitifire version was very old, it alternatively may have just been me using it incorrectly. Have you managed to...

Nice, adding ``` "-D_USE_MATH_DEFINES", ``` to nvcc flags is a better alternative Compiling with c++17 isn't enough, I get the errors listed above. Rn I'm trying to get c++20 working,...

Okay I've successfully ran inference on Windows. I'm in python 3.9 cuda 12.1 I had to do the following things: (do all of the following in x64 Native Tools Command...

> I am wondering, is it possible to add only a variant of `ggml_pad` with circular padding, use that as separate operation before the convolutions, then do the convolution without...

Ok it should be ready now

@CISC ty, made a pr here https://github.com/ggml-org/llama.cpp/pull/16985

Some conflicts, lemme resolve those...

Needs to be modified slightly bc you can do it only circular pad no circular conv

In particular like this: ``` __STATIC_INLINE__ struct ggml_tensor* ggml_nn_conv_2d(struct ggml_context* ctx, struct ggml_tensor* x, struct ggml_tensor* w, struct ggml_tensor* b, int s0 = 1, int s1 = 1, int p0...