You are not logged in.
Pages: 1
I'm testing Stable Diffusion on my own device.
when i tried to run a model, python returns with
OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacty of 3.71 GiB of which 16.44 MiB is free. Including non-PyTorch memory, this process has 94.00 MiB memory in use. Of the allocated memory 0 bytes is allocated by PyTorch, and 0 bytes is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONFhere's the output of nvidia-smi when running
Tue Aug 27 12:28:33 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3050 ... Off | 00000000:01:00.0 Off | N/A |
| N/A 40C P8 6W / 60W | 3786MiB / 4096MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 2429 G /usr/lib/Xorg 4MiB |
| 0 N/A N/A 5446 C venv/bin/python 94MiB |
+-----------------------------------------------------------------------------------------+here's nvidia-smi when not running
Tue Aug 27 12:35:49 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3050 ... Off | 00000000:01:00.0 Off | N/A |
| N/A 47C P8 8W / 60W | 10MiB / 4096MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 2429 G /usr/lib/Xorg 4MiB |
+-----------------------------------------------------------------------------------------+I'm using the driver downloaded from the nvidia site, cuda from pacman
nvcc -v:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Jun__6_02:18:23_PDT_2024
Cuda compilation tools, release 12.5, V12.5.82
Build cuda_12.5.r12.5/compiler.34385749_0Last edited by hanyixuanten (2024-08-27 05:28:08)
Offline
solved. just launch with --lowvram
Offline
Pages: 1