API tools faq
paste
delagarde

Invoke GGUF Error

delagarde
Apr 30th, 2025
29
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 6.74 KB | None | 0 0
raw download clone embed print report
  1. [2025-05-01 00:49:08,127]::[InvokeAI]::INFO --> Executing queue item 110, session 15cc97c7-0676-4463-8f1d-f1baf24c94ec
  2.  
  3. Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
  4. Loading checkpoint shards: 100%|##########| 2/2 [00:00<00:00, 24.69it/s]
  5. [2025-05-01 00:49:30,784]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '67d6d2ef-41f7-4d0d-8b02-b8d83777e64e:text_encoder_2' (T5EncoderModel) onto cuda device in 22.48s. Total model size: 9083.39MB, VRAM: 9083.39MB (100.0%)
  6. [2025-05-01 00:49:30,971]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '67d6d2ef-41f7-4d0d-8b02-b8d83777e64e:tokenizer_2' (T5Tokenizer) onto cuda device in 0.00s. Total model size: 0.03MB, VRAM: 0.00MB (0.0%)
  7. [2025-05-01 00:49:32,021]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'ebac0f34-ba8c-473a-bb7a-c6d8eebe2597:text_encoder' (CLIPTextModel) onto cuda device in 0.07s. Total model size: 469.44MB, VRAM: 469.44MB (100.0%)
  8. [2025-05-01 00:49:32,104]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model 'ebac0f34-ba8c-473a-bb7a-c6d8eebe2597:tokenizer' (CLIPTokenizer) onto cuda device in 0.00s. Total model size: 0.00MB, VRAM: 0.00MB (0.0%)
  9. [2025-05-01 00:49:32,178]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '4afeb13f-24e9-40b8-8cbb-a660d84dc559:transformer' (Flux) onto cuda device in 0.00s. Total model size: 12119.51MB, VRAM: 12119.51MB (100.0%)
  10.  
  11. 0%| | 0/19 [00:00<?, ?it/s]
  12. 0%| | 0/19 [00:00<?, ?it/s]
  13. [2025-05-01 00:49:32,183]::[InvokeAI]::ERROR --> Error while invoking session 15cc97c7-0676-4463-8f1d-f1baf24c94ec, invocation 351a1462-41d8-4201-b581-ff5c888e133f (flux_denoise): Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)
  14. [2025-05-01 00:49:32,183]::[InvokeAI]::ERROR --> Traceback (most recent call last):
  15. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\app\services\session_processor\session_processor_default.py", line 129, in run_node
  16. output = invocation.invoke_internal(context=context, services=self._services)
  17. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  18. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 212, in invoke_internal
  19. output = self.invoke(context)
  20. ^^^^^^^^^^^^^^^^^^^^
  21. File "E:\ai\invoke\.venv\Lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
  22. return func(*args, **kwargs)
  23. ^^^^^^^^^^^^^^^^^^^^^
  24. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 155, in invoke
  25. latents = self._run_diffusion(context)
  26. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  27. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\app\invocations\flux_denoise.py", line 379, in _run_diffusion
  28. x = denoise(
  29. ^^^^^^^^
  30. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\backend\flux\denoise.py", line 75, in denoise
  31. pred = model(
  32. ^^^^^^
  33. File "E:\ai\invoke\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
  34. return self._call_impl(*args, **kwargs)
  35. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  36. File "E:\ai\invoke\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
  37. return forward_call(*args, **kwargs)
  38. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  39. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\backend\flux\model.py", line 110, in forward
  40. img = self.img_in(img)
  41. ^^^^^^^^^^^^^^^^
  42. File "E:\ai\invoke\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
  43. return self._call_impl(*args, **kwargs)
  44. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  45. File "E:\ai\invoke\.venv\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
  46. return forward_call(*args, **kwargs)
  47. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  48. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\backend\model_manager\load\model_cache\torch_module_autocast\custom_modules\custom_linear.py", line 84, in forward
  49. return super().forward(input)
  50. ^^^^^^^^^^^^^^^^^^^^^^
  51. File "E:\ai\invoke\.venv\Lib\site-packages\torch\nn\modules\linear.py", line 125, in forward
  52. return F.linear(input, self.weight, self.bias)
  53. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  54. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\backend\quantization\gguf\ggml_tensor.py", line 161, in __torch_dispatch__
  55. return GGML_TENSOR_OP_TABLE[func](func, args, kwargs)
  56. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  57. File "E:\ai\invoke\.venv\Lib\site-packages\invokeai\backend\quantization\gguf\ggml_tensor.py", line 22, in dequantize_and_run
  58. return func(*dequantized_args, **dequantized_kwargs)
  59. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  60. File "E:\ai\invoke\.venv\Lib\site-packages\torch\_ops.py", line 723, in __call__
  61. return self._op(*args, **kwargs)
  62. ^^^^^^^^^^^^^^^^^^^^^^^^^
  63. RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)
  64.  
  65. [2025-05-01 00:49:32,203]::[InvokeAI]::INFO --> Graph stats: 15cc97c7-0676-4463-8f1d-f1baf24c94ec
  66. Node Calls Seconds VRAM Used
  67. flux_model_loader 1 0.001s 0.314G
  68. flux_text_encoder 1 24.010s 9.653G
  69. collect 1 0.001s 9.650G
  70. core_metadata 1 0.001s 9.650G
  71. img_resize 3 0.002s 9.650G
  72. flux_vae_encode 1 0.000s 9.650G
  73. tomask 1 0.000s 9.650G
  74. create_gradient_mask 1 0.001s 9.650G
  75. expand_mask_with_fade 1 0.000s 9.650G
  76. flux_denoise 1 0.029s 9.662G
  77. TOTAL GRAPH EXECUTION TIME: 24.045s
  78. TOTAL GRAPH WALL TIME: 24.047s
  79. RAM used by InvokeAI process: 12.68G (+0.081G)
  80. RAM used to load models: 21.16G
  81. VRAM in use: 9.650G
  82. RAM cache statistics:
  83. Model cache hits: 5
  84. Model cache misses: 4
  85. Models cached: 7
  86. Models cleared from cache: 0
  87. Cache high water mark: 21.41/0.00G
  88.  
  89. E:\ai\invoke\.venv\Lib\site-packages\huggingface_hub\utils\_deprecation.py:131: FutureWarning: 'get_token_permission' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '1.0'. Permissions are more complex than when `get_token_permission` was first introduced. OAuth and fine-grain tokens allows for more detailed permissions. If you need to know the permissions associated with a token, please use `whoami` and check the `'auth'` key.
  90. warnings.warn(warning_message, FutureWarning)
Tags: Invoke GGUF
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!