is it possible to get it work with ComfyUI-Zluda. This error comes up:
File "X:\ComfyUI-Zluda\execution.py", line 496, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\execution.py", line 315, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "X:\ComfyUI-Zluda\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\nodes\single_speaker_node.py", line 214, in generate_speech
raise Exception(f"Error generating speech: {str(e)}")
2025-09-11T10:46:01.455428 - [START] Security scan2025-09-11T10:46:01.455428 -
2025-09-11T10:46:01.933038 - [DONE] Security scan2025-09-11T10:46:01.934042 -
2025-09-11T10:46:02.097552 - ## ComfyUI-Manager: installing dependencies done.2025-09-11T10:46:02.097552 -
2025-09-11T10:46:02.097552 - ** ComfyUI startup time:2025-09-11T10:46:02.097552 - 2025-09-11T10:46:02.097552 - 2025-09-11 10:46:02.0972025-09-11T10:46:02.097552 -
2025-09-11T10:46:02.097552 - ** Platform:2025-09-11T10:46:02.097552 - 2025-09-11T10:46:02.097552 - Windows2025-09-11T10:46:02.097552 -
2025-09-11T10:46:02.097552 - ** Python version:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.098555 - ** Python executable:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - X:\ComfyUI-Zluda\venv\Scripts\python.exe2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.098555 - ** ComfyUI Path:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - X:\ComfyUI-Zluda2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.098555 - ** ComfyUI Base Folder Path:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - X:\ComfyUI-Zluda2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.098555 - ** User directory:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - X:\ComfyUI-Zluda\user2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.098555 - ** ComfyUI-Manager config path:2025-09-11T10:46:02.098555 - 2025-09-11T10:46:02.098555 - X:\ComfyUI-Zluda\user\default\ComfyUI-Manager\config.ini2025-09-11T10:46:02.098555 -
2025-09-11T10:46:02.099559 - ** Log path:2025-09-11T10:46:02.099559 - 2025-09-11T10:46:02.099559 - X:\ComfyUI-Zluda\user\comfyui.log2025-09-11T10:46:02.099559 -
2025-09-11T10:46:02.663541 -
Prestartup times for custom nodes:
2025-09-11T10:46:02.663541 - 1.4 seconds: X:\ComfyUI-Zluda\custom_nodes\ComfyUI-Manager
2025-09-11T10:46:02.663541 -
2025-09-11T10:46:03.023991 - X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\cuda\__init__.py:61: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
import pynvml # type: ignore[import]
2025-09-11T10:46:03.526302 - Checkpoint files will always be loaded safely.
2025-09-11T10:46:03.965906 - �[93m%%% [backported] imported triton knobs�[0m2025-09-11T10:46:03.966909 -
2025-09-11T10:46:04.114419 -
:: Checking package versions...2025-09-11T10:46:04.114419 -
2025-09-11T10:46:04.116426 - Found pydantic: 2.11.7, pydantic-settings: 2.10.12025-09-11T10:46:04.116426 -
2025-09-11T10:46:04.153554 - :: Pydantic packages are compatible, skipping reinstall2025-09-11T10:46:04.154559 -
2025-09-11T10:46:04.154559 - Installed version of comfyui-frontend-package: 1.25.112025-09-11T10:46:04.154559 -
2025-09-11T10:46:04.156565 - Installed version of comfyui-workflow-templates: 0.1.762025-09-11T10:46:04.156565 -
2025-09-11T10:46:04.156565 - Installed version of av: 14.4.02025-09-11T10:46:04.156565 -
2025-09-11T10:46:04.156565 - Installed version of comfyui-embedded-docs: 0.2.62025-09-11T10:46:04.156565 -
2025-09-11T10:46:04.156565 - :: Package version check complete.2025-09-11T10:46:04.156565 -
2025-09-11T10:46:04.156565 -
:: ------------------------ ZLUDA ----------------------- :: 2025-09-11T10:46:04.157568 -
2025-09-11T10:46:04.206605 - :: TRITON_OVERRIDE_ARCH already set to: gfx12012025-09-11T10:46:04.206605 -
2025-09-11T10:46:04.206605 - :: Triton core imported successfully2025-09-11T10:46:04.206605 -
2025-09-11T10:46:04.207610 - :: Enabled cuDNN2025-09-11T10:46:04.207610 -
2025-09-11T10:46:04.208613 - :: Running Triton kernel test...2025-09-11T10:46:04.208613 -
2025-09-11T10:46:04.555750 - �[93m%%% [info] triton/runtime/build/platform_key: AMD64,Windows,64bit,WindowsPE�[0m2025-09-11T10:46:04.556711 -
2025-09-11T10:46:05.182058 - :: Triton kernel test passed successfully2025-09-11T10:46:05.182058 -
2025-09-11T10:46:05.183059 - :: Triton initialized successfully2025-09-11T10:46:05.183059 -
2025-09-11T10:46:05.213373 - :: Patching ONNX Runtime for ZLUDA — disabling CUDA EP.2025-09-11T10:46:05.213373 -
2025-09-11T10:46:05.213373 - :: Using ZLUDA with device: AMD Radeon RX 9070 XT [ZLUDA]2025-09-11T10:46:05.213373 -
2025-09-11T10:46:05.213373 - :: Applying core ZLUDA patches...2025-09-11T10:46:05.213373 -
2025-09-11T10:46:05.213373 - :: Initializing Triton optimizations2025-09-11T10:46:05.213373 -
2025-09-11T10:46:05.213373 - :: Configuring Triton device properties...2025-09-11T10:46:05.214376 -
2025-09-11T10:46:05.214376 - :: Triton device properties configured2025-09-11T10:46:05.214376 -
2025-09-11T10:46:05.241421 - :: Flash attention components found2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: AMD flash attention enabled successfully2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: Configuring PyTorch backends...2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: Disabled CUDA flash attention2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: Enabled math attention fallback2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: ZLUDA initialization complete2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.241421 - :: ------------------------ ZLUDA ----------------------- ::
2025-09-11T10:46:05.241421 -
2025-09-11T10:46:05.245780 - Total VRAM 16304 MB, total RAM 128617 MB
2025-09-11T10:46:05.245780 - pytorch version: 2.7.0+cu118
2025-09-11T10:46:05.246781 - Set vram state to: NORMAL_VRAM
2025-09-11T10:46:05.246781 - Device: cuda:0 AMD Radeon RX 9070 XT [ZLUDA] : native
2025-09-11T10:46:05.419688 - Using sub quadratic optimization for attention, if you have memory or speed issues try using: --use-split-cross-attention
2025-09-11T10:46:06.356982 - Python version: 3.11.9 (tags/v3.11.9:de54cf5, Apr 2 2024, 10:12:12) [MSC v.1938 64 bit (AMD64)]
2025-09-11T10:46:06.356982 - ComfyUI version: 0.3.58
2025-09-11T10:46:06.386493 - ComfyUI frontend version: 1.25.11
2025-09-11T10:46:06.387497 - [Prompt Server] web root: X:\ComfyUI-Zluda\venv\Lib\site-packages\comfyui_frontend_package\static
2025-09-11T10:46:07.005457 - ### Loading: ComfyUI-Manager (V3.36)
2025-09-11T10:46:07.005457 - [ComfyUI-Manager] network_mode: public
2025-09-11T10:46:07.321632 - ### ComfyUI Revision: 5047 [dc866c0e] | Released on '2025-09-10'
2025-09-11T10:46:07.653592 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
2025-09-11T10:46:07.664397 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
2025-09-11T10:46:07.706893 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
2025-09-11T10:46:07.739722 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
2025-09-11T10:46:07.786720 - [ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
2025-09-11T10:46:07.802277 - APEX FusedRMSNorm not available, using native implementation
2025-09-11T10:46:08.211175 - [VibeVoice] SageAttention available for acceleration
2025-09-11T10:46:08.212179 - [VibeVoice] Using embedded VibeVoice (MIT licensed)
2025-09-11T10:46:08.213186 - [VibeVoice] VibeVoice nodes registered successfully
2025-09-11T10:46:08.213186 -
Import times for custom nodes:
2025-09-11T10:46:08.213186 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\cfz_vae_loader.py
2025-09-11T10:46:08.213186 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\cfz_cudnn.toggle.py
2025-09-11T10:46:08.213186 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\websocket_image_save.py
2025-09-11T10:46:08.213186 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\cfz_patcher.py
2025-09-11T10:46:08.213186 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\ComfyUI-deepcache
2025-09-11T10:46:08.214501 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\CFZ-caching
2025-09-11T10:46:08.214501 - 0.0 seconds: X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI
2025-09-11T10:46:08.214501 - 0.6 seconds: X:\ComfyUI-Zluda\custom_nodes\ComfyUI-VibeVoice
2025-09-11T10:46:08.214501 - 0.6 seconds: X:\ComfyUI-Zluda\custom_nodes\ComfyUI-Manager
2025-09-11T10:46:08.214501 -
2025-09-11T10:46:08.343224 - Context impl SQLiteImpl.
2025-09-11T10:46:08.343224 - Will assume non-transactional DDL.
2025-09-11T10:46:08.344226 - No target revision found.
2025-09-11T10:46:08.350705 - Starting server
2025-09-11T10:46:08.351969 - To see the GUI go to: http://127.0.0.1:8188
2025-09-11T10:46:09.111487 - [CFZ Load] No cache files found2025-09-11T10:46:09.111487 -
2025-09-11T10:46:09.112492 - [CFZ Load] No cache files found2025-09-11T10:46:09.112492 -
2025-09-11T10:46:11.192301 - FETCH ComfyRegistry Data: 5/972025-09-11T10:46:11.192301 -
2025-09-11T10:46:11.768135 - got prompt
2025-09-11T10:46:11.821473 - APEX FusedRMSNorm not available, using native implementation
2025-09-11T10:46:11.836639 - [VibeVoice] Using embedded VibeVoice from X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed
2025-09-11T10:46:11.837642 - [VibeVoice] Using auto attention implementation selection
2025-09-11T10:46:11.837642 - [VibeVoice] Loading model from local cache: aoi-ot/VibeVoice-Large
2025-09-11T10:46:14.110696 -
Loading checkpoint shards: 10%|█████▌ | 1/10 [00:01<00:15, 1.77s/it]2025-09-11T10:46:15.064847 - FETCH ComfyRegistry Data: 10/972025-09-11T10:46:15.064847 -
2025-09-11T10:46:17.479852 -
Loading checkpoint shards: 30%|████████████████▊ | 3/10 [00:05<00:11, 1.71s/it]2025-09-11T10:46:18.760629 - FETCH ComfyRegistry Data: 15/972025-09-11T10:46:18.760629 -
2025-09-11T10:46:20.877943 -
Loading checkpoint shards: 50%|████████████████████████████ | 5/10 [00:08<00:08, 1.70s/it]2025-09-11T10:46:22.503617 - FETCH ComfyRegistry Data: 20/972025-09-11T10:46:22.503617 -
2025-09-11T10:46:25.855884 -
Loading checkpoint shards: 80%|████████████████████████████████████████████▊ | 8/10 [00:13<00:03, 1.66s/it]2025-09-11T10:46:25.912079 - FETCH ComfyRegistry Data: 25/972025-09-11T10:46:25.912079 -
2025-09-11T10:46:28.991622 -
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████| 10/10 [00:16<00:00, 1.62s/it]2025-09-11T10:46:28.991622 -
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████| 10/10 [00:16<00:00, 1.67s/it]2025-09-11T10:46:28.991622 -
2025-09-11T10:46:29.299968 - No preprocessor_config.json found at aoi-ot/VibeVoice-Large, using defaults
2025-09-11T10:46:29.299968 - Loading tokenizer from Qwen/Qwen2.5-1.5B
2025-09-11T10:46:29.474300 - FETCH ComfyRegistry Data: 30/972025-09-11T10:46:29.474300 -
2025-09-11T10:46:29.477443 - [VibeVoice] Processing text segment 1 (11 words)
2025-09-11T10:46:29.516401 - [VibeVoice] Starting audio generation with 20 diffusion steps...
2025-09-11T10:46:29.526083 - [VibeVoice] Generating audio with 20 diffusion steps...
2025-09-11T10:46:29.526083 - [VibeVoice] Note: Progress bar shows max possible tokens, not actual needed (~32 estimated)
2025-09-11T10:46:29.526083 - [VibeVoice] The generation will stop automatically when audio is complete
2025-09-11T10:46:29.887739 -
Generating (active: 1/1): 0%| | 0/572 [00:00<?, ?it/s]2025-09-11T10:46:33.063362 - FETCH ComfyRegistry Data: 35/972025-09-11T10:46:33.063362 -
2025-09-11T10:46:36.438592 - FETCH ComfyRegistry Data: 40/972025-09-11T10:46:36.438592 -
2025-09-11T10:46:40.154268 - FETCH ComfyRegistry Data: 45/972025-09-11T10:46:40.154268 -
2025-09-11T10:46:41.518354 -
2025-09-11T10:46:41.518354 - [VibeVoice] VibeVoice generation failed: GET was unable to find an engine to execute this computation
2025-09-11T10:46:41.518354 - [VibeVoice] Single speaker speech generation failed: VibeVoice generation failed: GET was unable to find an engine to execute this computation
2025-09-11T10:46:41.523299 - !!! Exception during processing !!! Error generating speech: VibeVoice generation failed: GET was unable to find an engine to execute this computation
2025-09-11T10:46:41.526703 - Traceback (most recent call last):
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\nodes\base_vibevoice.py", line 825, in _generate_with_vibevoice
output = self.model.generate(
^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modeling_vibevoice_inference.py", line 565, in generate
outputs = self(
^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modeling_vibevoice_inference.py", line 286, in forward
acoustic_features, speech_embeds = self._process_speech_inputs(speech_tensors.to(self.dtype), speech_masks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modeling_vibevoice_inference.py", line 218, in _process_speech_inputs
encoder_output = self.model.acoustic_tokenizer.encode(speech_tensors.unsqueeze(1))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 1084, in encode
latents = self.encoder(audio, cache=cache, sample_indices=sample_indices, use_cache=use_cache, debug=debug)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 811, in forward
x = self.forward_features(x, cache=cache, sample_indices=sample_indices, use_cache=use_cache, debug=debug)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 781, in forward_features
x = layer(x, cache=cache, sample_indices=sample_indices, use_cache=use_cache, debug=debug)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 318, in forward
return self._forward_non_streaming(x, debug=debug)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 413, in _forward_non_streaming
output = self.conv(x)
^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\vvembed\modular\modular_vibevoice_tokenizer.py", line 173, in forward
x = self.conv(x)
^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\conv.py", line 375, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\venv\Lib\site-packages\torch\nn\modules\conv.py", line 370, in _conv_forward
return F.conv1d(
^^^^^^^^^
RuntimeError: GET was unable to find an engine to execute this computation
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\nodes\single_speaker_node.py", line 160, in generate_speech
segment_audio = self._generate_with_vibevoice(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\nodes\base_vibevoice.py", line 872, in _generate_with_vibevoice
raise Exception(f"VibeVoice generation failed: {str(e)}")
Exception: VibeVoice generation failed: GET was unable to find an engine to execute this computation
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "X:\ComfyUI-Zluda\execution.py", line 496, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\execution.py", line 315, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "X:\ComfyUI-Zluda\execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "X:\ComfyUI-Zluda\execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "X:\ComfyUI-Zluda\custom_nodes\VibeVoice-ComfyUI\nodes\single_speaker_node.py", line 214, in generate_speech
raise Exception(f"Error generating speech: {str(e)}")
Exception: Error generating speech: VibeVoice generation failed: GET was unable to find an engine to execute this computation
2025-09-11T10:46:41.527704 - Prompt executed in 29.76 seconds
`
Hi,
is it possible to get it work with ComfyUI-Zluda. This error comes up:
Error generating speech: VibeVoice generation failed: GET was unable to find an engine to execute this computation`
ComfyUI Error Report
Error Details
Stack Trace
System Information
Devices
Logs