#5740 CUDA error: device-side assert triggeredCompile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

CUDA error: device-side assert triggered
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
,Traceback (most recent call last):
File "D:\ass\voiceVideo\carryVdeo\pyvideotrans\videotrans\process\tts_fun.py", line 121, in qwen3tts_fun

wavs, sr = BASE_OBJ.generate_voice_clone(**kw)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\qwen_tts\inference\qwen3_tts_model.py", line 603, in generate_voice_clone

talker_codes_list, _ = self.model.generate(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\qwen_tts\core\models\modeling_qwen3_tts.py", line 2272, in generate

talker_result =

......
,kwargs=kwargs)
File "D:\ass\voiceVideo\carryVdeo\pyvideotrans\videotrans\configure\base.py", line 272, in _new_process

raise VideoTransError(err)

videotrans.configure.excepts.VideoTransError: CUDA error: device-side assert triggered
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
,Traceback (most recent call last):
File "D:\ass\voiceVideo\carryVdeo\pyvideotrans\videotrans\process\tts_fun.py", line 121, in qwen3tts_fun

wavs, sr = BASE_OBJ.generate_voice_clone(**kw)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\qwen_tts\inference\qwen3_tts_model.py", line 603, in generate_voice_clone

talker_codes_list, _ = self.model.generate(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\qwen_tts\core\models\modeling_qwen3_tts.py", line 2272, in generate

talker_result = self.talker.generate(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\transformers4576\generation\utils.py", line 2566, in generate

result = decoding_method(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\transformers4576\generation\utils.py", line 2789, in _sample

outputs = model_forward(**model_inputs, return_dict=True)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl

return forward_call(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\transformers4576\utils\generic.py", line 918, in wrapper

output = func(self, *args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\qwen_tts\core\models\modeling_qwen3_tts.py", line 1671, in forward

predictor_result = self.code_predictor.generate(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\transformers4576\generation\utils.py", line 2566, in generate

result = decoding_method(

File "D:\ass\voiceVideo\carryVdeo\pyvideotrans.venv\lib\site-packages\transformers4576\generation\utils.py", line 2831, in _sample

next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)

RuntimeError: CUDA error: device-side assert triggered
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 单视频模式
原始输入文件名: G:/静观项目_私与公/静观项目_私与公2026.3.16/文-文宣项目/文-文宣项目-音视门/database/carry/youtube/segment_000.mp4,
输出结果保存到文件夹: D:/ass/voiceVideo/carryVdeo/pyvideotrans/output/segment_000-mp4,
临时文件夹: D:/ass/voiceVideo/carryVdeo/pyvideotrans/tmp/3912/f0581eaed1
已选 清理已存在
已选 启用CUDA加速
未选 降噪
语音识别:faster-whisper(本地内置), model_name: large-v3-turbo, 发音语言: 英语, 断句方式:默认断句
翻译渠道:M2M100(本地内置),原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
配音渠道:Qwen3-TTS(本地内置), 角色:clone, 配音语言:简体中文, 未选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
字幕: 嵌入硬字幕
已选 分离人声与背景声, 已选 重新嵌入背景声, 背景音量0.8, 背景声音时长 短于 视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件
已选 仅输出mp4
代理地址: