[GH-ISSUE #1889] RuntimeError: CUDA error: out of memory #1268

New issue

Closed

opened 2026-10-20 10:07:32 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-20 10:07:32 +00:00

Owner

Originally created by @MoonEsther on GitHub (Mar 17, 2024).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1889

just open go-realtime-gui.bat
It worked fine with a rtx1650 4g

now worked with rtx1660ti 6g,like this

is_half:False, device:cuda:0
Input device: 1:麦克风 (2- USB Audio Device) (MME)
Output device: 3:扬声器 (2- USB Audio Device) (MME)
cuda_is_available: True
Traceback (most recent call last):
File "E:\AI\RVC1006Nvidia\tools\rvc_for_realtime.py", line 102, in init
hubert_model = hubert_model.to(self.device)
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1145, in to
return self._apply(convert)
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply
param_applied = fn(param)
File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Originally created by @MoonEsther on GitHub (Mar 17, 2024). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1889 just open go-realtime-gui.bat It worked fine with a rtx1650 4g now worked with rtx1660ti 6g,like this is_half:False, device:cuda:0 Input device: 1:麦克风 (2- USB Audio Device) (MME) Output device: 3:扬声器 (2- USB Audio Device) (MME) cuda_is_available: True Traceback (most recent call last): File "E:\AI\RVC1006Nvidia\tools\rvc_for_realtime.py", line 102, in __init__ hubert_model = hubert_model.to(self.device) File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1145, in to return self._apply(convert) File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) [Previous line repeated 1 more time] File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply param_applied = fn(param) File "E:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

bsakaguchi

2026-10-20 10:07:32 +00:00

closed this issue
added the
stale
label

bsakaguchi commented

2026-10-20 10:07:33 +00:00

Author

Owner

@github-actions[bot] commented on GitHub (May 3, 2024):

This issue was closed because it has been inactive for 15 days since being marked as stale.

@github-actions[bot] commented on GitHub (May 3, 2024): This issue was closed because it has been inactive for 15 days since being marked as stale.