[GH-ISSUE #1957] error rvc #1326

New issue

Open

opened 2026-10-20 10:08:05 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-20 10:08:05 +00:00

Owner

Originally created by @hijxmmy on GitHub (Apr 9, 2024).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1957

Traceback (most recent call last):
File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\rvcgui.py", line 129, in vc_single
audio_opt = vc.pipeline(
File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\vc_infer_pipeline.py", line 326, in pipeline
sid = torch.tensor(sid, device=self.device).unsqueeze(0).long()
RuntimeError: CUDA error: the launch timed out and was terminated
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 @hijxmmy on GitHub (Apr 9, 2024). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/1957 Traceback (most recent call last): File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\rvcgui.py", line 129, in vc_single audio_opt = vc.pipeline( File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\vc_infer_pipeline.py", line 326, in pipeline sid = torch.tensor(sid, device=self.device).unsqueeze(0).long() RuntimeError: CUDA error: the launch timed out and was terminated 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 added the

help wanted

bug

labels

2026-10-20 10:08:05 +00:00

bsakaguchi commented

2026-10-20 10:08:06 +00:00

Author

Owner

@arbazw commented on GitHub (Jun 21, 2024):

Set the environment variable CUDA_LAUNCH_BLOCKING=1 before running your application. This makes CUDA API calls synchronous, providing more accurate error messages and stack traces.

export CUDA_LAUNCH_BLOCKING=1

@arbazw commented on GitHub (Jun 21, 2024): Set the environment variable `CUDA_LAUNCH_BLOCKING=1` before running your application. This makes CUDA API calls synchronous, providing more accurate error messages and stack traces. `export CUDA_LAUNCH_BLOCKING=1`