Arthur Aardvark

After just dealing with this nightmare again and stumbling upon this thread as I try to figure out how to resolve my issues, I'd just like to throw my hat...

> They are. I've been examining both the look and the histograms of the examples (I need to download the node and generate some 16bpc outputs or EXR) and from...

> We'd love to have this. Our first priority is quantization but when we have the bandwidth we can look into adding Flash attention. (Note PRs are welcome) I'd messaged...

To add to the mix, EXL2, it is not only an inference lib that can load GPTQ models, but when a model is instead quantized by EXL2, it performs better...

I'd also like this. I'll mention `mise integrate python@xxx` but I'd prefer plain ol' `mise install python@xxx -s / --sys / --system` And there could be an environmental variable one...

It would seem to be an issue for me, but I'll still consider this serendipity 😂 I was getting `RuntimeError: Internal: src/sentencepiece_processor.cc(1103) [model_proto->ParseFromArray(serialized.data(), serialized.size())]` for my Deepseek-Coder-33b model off of...

Sigh, well, I give up, that was working to a good degree, just had some trouble first with the tokenizer file, kept trying to use HF remote repo data in...

This could really use to be done. This was going to be my first dive into Rustdom but it feels too involved to get it up and running. It seems...

I suppose this is a differing issue, but the man pages of corepack (node v21+) state one can also use `corepack install yarn@*` https://nodejs.org/api/corepack.html To install the latest pnpm. That...

> Added a custom function plugin support that opens up some exciting possibilities. With this addition, we can integrate custom functions into our RAG pipeline or utilise it for post-processing...