Vito Plantamura

you should post this in the pytorch repo :-) In the past, I had a similar error, and I solved it by installing the most recent Pytorch nightly build. Vito

hi, sorry for the late answer. XNNPACK provides a set of operators for quantized operations (including 8-bit operations) as well. It may seem counterintuitive, but making "fast" 8-bit operators is...

hi, I noticed this effect too. If you try to generate an image here: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0?text=an+astronaut+riding+a+horse+on+mars it is possible to notice the same effect, but I think it is less visible...

hi, the OnnxStream models are exported directly from the Hugging Face SDXL models, so the inference result should be numerically (almost) the same. But I think I understand what the...

hi, HF Diffusers support loading safetensor files, so I don't think I quite understand your question :-) More info here: https://github.com/vitoplantamura/OnnxStream#how-to-convert-and-run-a-custom-stable-diffusion-15-model-with-onnxstream-by-gaelicthunder Vito

ok, got it. I will definitely look at how AMDGPU_TARGETS works in llama.cpp. Regarding the issue of activations quantization, I suspect that it can't be done, but obviously I have...

no, the safetensor file needs to be first converted to the format compatible with OnnxStream. This is not a simple procedure. The link I posted before explains how to do...

really interesting! I took a look at the code: the idea of ​​a single project that manages the entire conversion process is excellent! I plan to try it ASAP! Thanks,...

hi AeroX2, I finally found the time to try your project calmly and it works flawlessly. I tried with a LoRA model for SDXL, modifying the code a bit (such...

no, obviously :-) What exactly is the command in question and the related error message? LivingLinux made a very cool video on this topic a few days ago: https://www.youtube.com/watch?v=_2Snbo7uA9E Vito