stable-diffusion-webui-amdgpu-forge icon indicating copy to clipboard operation
stable-diffusion-webui-amdgpu-forge copied to clipboard

rocBLAS error: Could not load C:\Program Files\AMD\ROCm\6.2\bin\/rocblas/library/TensileLibrary_lazy_gfx1036.dat

Open hjklove opened this issue 7 months ago • 3 comments

venv "E:\sd-zluda\stable-diffusion-webui-amdgpu-forge\venv\Scripts\Python.exe" WARNING: ZLUDA works best with SD.Next. Please consider migrating to SD.Next. fatal: No names found, cannot describe anything. Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: f2.0.1v1.10.1-1.10.1 Commit hash: e07be6a48fc0ae1840b78d5e55ee36ab78396b30 ROCm: no agent was found ROCm: version=6.2 ZLUDA support: experimental ZLUDA load: path='E:\sd-zluda\stable-diffusion-webui-amdgpu-forge.zluda' nightly=False Launching Web UI with arguments: --use-zluda --cuda-stream --attention-quad Total VRAM 12456 MB, total RAM 31849 MB pytorch version: 2.6.0+cu118 Set vram state to: NORMAL_VRAM Device: cuda:0 AMD Radeon(TM) Graphics [ZLUDA] : native VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16 CUDA Using Stream: True Using sub quadratic optimization for cross attention Using split attention for VAE ONNX: version=1.21.1 provider=CPUExecutionProvider, available=['AzureExecutionProvider', 'CPUExecutionProvider']

rocBLAS error: Could not load C:\Program Files\AMD\ROCm\6.2\bin/rocblas/library/TensileLibrary_lazy_gfx1036.dat

rocBLAS error: Could not initialize Tensile library

hjklove avatar May 07 '25 13:05 hjklove

try using --device-id 1 in the arguments

heeyfox avatar May 09 '25 01:05 heeyfox

try using --device-id 1 in the arguments

Yes I have used it, this is the error code for using --device-id 1

hjklove avatar May 09 '25 12:05 hjklove

Its trying to use your CPUs iGPU. The easiest fix is to disable Radeon TM Graphics in the Display Driver section of the Device Manager. Then relaunch.

CS1o avatar May 09 '25 18:05 CS1o