Closed joebnb closed 1 month ago
https://hub.docker.com/r/intel/intel-optimized-pytorch seems intel take advantage alot
@gyang1099, can you please help on this?
@joebnb , providing both XRT and XRT plugin packages are installed on the host system, run your docker container with additional option "--privileged -v /dev/accel:/dev/accel" to gain access to RyzenAI device, you can then run the example_noop_test or your model inference in the container
i using default config build get this error
make[4]: *** [Makefile:1934: .] Error 2
make[3]: *** [debian/rules:74: build-arch] Error 2
dpkg-buildpackage: error: make -f debian/rules binary subprocess returned exit status 2
make[2]: *** [scripts/Makefile.package:121: bindeb-pkg] Error 2
make[1]: *** [/root/linux/Makefile:1555: bindeb-pkg] Error 2
make: *** [Makefile:240: __sub-make] Error 2
would offering some release build by default,and write some document for use, i think many people was not know how to use this,7840 8845(this i'm using) are aleardy release over 1 year, greate chips but just few people know how to use
i was reading this repo commit history,maybe need more staff to help finish this,it's seems just one or two guys work on it
whats is this relation of xdna-driver should i install rocm ? should i do mapping of --device=/dev/kfd --device=/dev/dri and add arguments --cap-add=SYS_PTRACE
i fond there was already have prebuild driver,why there was not documented or do a release using github release
im tired maybe should sell this and buy a intel architecture machine
I want use amd chips to model inference on some docker container,like this image
https://hub.docker.com/r/siutin/stable-diffusion-webui-docker
but im not sure how to make amd gpu work with it.
would give some advice or document to explain how to make a cpu works docker image or linux system to extend ryzen ai support