Closed turion closed 1 year ago
Workaround seems to be to prepend HSA_OVERRIDE_GFX_VERSION=10.3.0
(https://stackoverflow.com/questions/73575955/pytorch-hiperrornobinaryforgpu-unable-to-find-code-object-for-all-current-devi), I don't really understand what it does though.
Hm, interesting. I have 6900xt and for me it works without an issue (except for slow start and warning about missing database or something). I'm curious, what is your GPU model ? Because it seems that for some GPUs are officially supported by ROCM, and some require this env variable to trick the driver into thinking that GPU has supported architecture - https://github.com/RadeonOpenCompute/ROCm/search?q=%27HSA_OVERRIDE_GFX_VERSION&type=issues .
Seems like I have a Ryzen 5650U with integrated GPU..? If that's a thing.
Yep, you could expect some limitations on integrated GPUs. Well, I'll pin this issue for reference to other folks who might face the same problem.
I have the same problem with an RX 5700 (i.e. a dedicated GPU).
HSA_OVERRIDE_GFX_VERSION=10.3.0
still works as a fix.
This should be in an FAQ section of the README imo.
@gbtb
I followed your instructions, but they didn't work: