segurac/force-host-alloction-apu

force-host-alloction-apu's Issues

GPU Hang on Stable Diffusion

If I try it with ollama it seems to work, but with stable diffusion my whole desktop freezes.
One time it restarted but I got this:

HW Exception by GPU node-1 (Agent handle: 0x632d71637310) reason :GPU Hang

I can't seem to be able to run Stable Diffusion with it.

Segmentation Fault on loading SD

I guess I need to confirm the use-case for this. I have an HP AMD-based Elitebook 705 G4 mini with a Ryzen 5 2400GE CPU. The BIOS doesn't allow me to set the iGPU dedicated RAM greater than 1GB. I was hoping to use this as a means to get around the BIOS limitation and have pytorch actually use the GTT shared RAM as VRAM. If it is not intended to allow pytorch/SD to do that, then the segfault is probably due to having only 1GB of VRAM available to ROCm and I'm out of luck trying to do anything other than CPU-only mode on this system.

I'm running Ubuntu 22.04, ROCm 5.6.1, Python 3.10.12. I get a segfault when trying to start SD:

./webui.sh: line 256: 49971 Segmentation fault (core dumped) "${python_cmd}" -u "${LAUNCH_SCRIPT}" "$@"

ROCm SMI output is below:

========================= ROCm System Management Interface =========================
=================================== Concise Info ===================================
GPU[0] : get_power_avg, Not supported on the given system
ERROR: GPU[0] : sclk clock is unsupported

GPU[0] : get_power_cap, Not supported on the given system
GPU Temp (DieEdge) AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU%
0 50.0c N/A None 933Mhz 0% auto Unsupported 7% 100%

=============================== End of ROCm SMI Log ================================

radeontop shows GTT memory is allocated as intended:

                                       71M / 1000M VRAM   7.14% x
                                       27M / 15498M GTT   0.17% x

I've tried various startup options, such as the one shown below, but continue to get the segfault error whatever options I choose.

LD_PRELOAD=/libforcegttalloc.so HSA_OVERRIDE_GFX_VERSION=10.3.0 ./webui.sh --listen --lowvram --opt-sub-quad-attention --precision full --no-half

Would appreciate a confirmation whether or not this should work. Thanks.