Cromefire_

> With higher level libraries (sharp, bimg, etc. etc.) able to implement something fancier if they wish. On that topic, it would probably be good as well to have a...

AMD in their new release of ROCm 6 will also do a lot of optimization around FP8 in `hipBLASLt` (and in general recommends that library for use in ML), could...

> hipBLASlt's github says it requires an AMD MI200-MI300 Instinct Accelerator GPU Too bad. Although it's AMD, so maybe I'll just try and build it on my XTX and see...

> When it comes to compiling models for specific architectures, you can always look at mlc: https://llm.mlc.ai/docs/index.html, I believe they're using an Apache compiler/framework to compile a model into extremely...

> Definitely share your results, I also have a 7900xtx! Nope, doesn't work, it requires `amdhsa_accum_offset` which is only available on CDNA2+ it seems.

I think I'm having the same issue. Sometimes the error message pops up and in the past few days I was able to just get it working with a few...

> if you could prep container with access to your GPU, Debian based and would find out how to install all dependencies it will help with quick start. Sure it...

The end of the investigation is it works fine in docker and worked immediately: ``` ~$ sudo docker run --rm --device /dev/dri -v /dev/dri/by-path:/dev/dri/by-path -it local/nextcloud:27.1.3-apache-intel-custom /usr/bin/python -c "import tensorflow...

> fails on GPU, it seems to try with CPU - these are the two places in the code I'd focus on to make another deviation to check on XPU/Intel...

> I'd probably replace the tfjs-node-gpu with the intel one Well that's what I'm trying to say, there is no Intel one... `@tensorflow/tfjs-node-gpu` first needs to support PluggableDevices, before we...