Mathieu Poumeyrol

Sorry for the delay, but the good news is, with the right set of options, I think we're good. We need to ignore both the internal values AND the output...

not a big surprise here. I will have a look, see if I can see anything obviously wrong in how tract does it. but don't hold your breath. it's very...

I noticed the dominating presence of Resize in the split. This operator is not completely optimized. it is a "big" operator, there are lot of combinations of options that may...

Just for fun and get an idea of the state of affair for non-llm model support on cuda: left is cuda, right is cpu: We're not there yet :) Only...

I was not suggesting this, Resize on Cuda on its own would have limited impact here, to leverage cuda, we need large sections of the model (ideally all of it)...

I am also thinking that onnxruntime probably does not go to the GPU if you don't ask for it. What I think it may do, on the other hand, is...

Hey, I'm happy to consider PRs addressing this issue. One absolute constraint being, it should come with no measurable runtime overhead on some models. I can't tell exactly which ones,...

Did some work on for dft "recent" extensions in #1905 . But this model present other challenges, it does not load yet. To be continued.

Hey, I can't find too much information about this operator. I can't find it in ONNX. I assume it is a microsoft / onnx-runtime extension ? Do you know if...

Hey ! Thanks for your interest, sorry it did not work out of the box for you. There is a (undocumented) flag you could try: add `deb_multiarch='aarch64-linux-gnu'` to the toolchain....