API tools faq
paste
A-Vladimir

Untitled

A-Vladimir
Nov 15th, 2025
63
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 10.18 KB | None | 0 0
raw download clone embed print report
  1. Started Invoke process with PID 7535
  2. bitsandbytes library load error: Configured ROCm binary not found at /mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_rocm63.so
  3. Traceback (most recent call last):
  4. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/bitsandbytes/cextension.py", line 313, in <module>
  5. lib = get_native_library()
  6. ^^^^^^^^^^^^^^^^^^^^
  7. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/bitsandbytes/cextension.py", line 282, in get_native_library
  8. raise RuntimeError(f"Configured {BNB_BACKEND} binary not found at {cuda_binary_path}")
  9. RuntimeError: Configured ROCm binary not found at /mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/bitsandbytes/libbitsandbytes_rocm63.so
  10. [2025-11-15 19:19:51,441]::[InvokeAI]::INFO --> Using torch device: Radeon RX 7900 XTX
  11. [2025-11-15 19:19:51,443]::[InvokeAI]::INFO --> cuDNN version: 3003000
  12. [2025-11-15 19:19:51,866]::[InvokeAI]::INFO --> Patchmatch initialized
  13. [2025-11-15 19:19:53,117]::[InvokeAI]::INFO --> InvokeAI version 6.9.0
  14. [2025-11-15 19:19:53,117]::[InvokeAI]::INFO --> Root directory = /mnt/Linux Files/InvokeAI
  15. [2025-11-15 19:19:53,117]::[InvokeAI]::INFO --> Initializing database at /mnt/Linux Files/InvokeAI/databases/invokeai.db
  16. [2025-11-15 19:19:53,120]::[ModelManagerService]::INFO --> [MODEL CACHE] Calculated model RAM cache size: 4096.00 MB. Heuristics applied: [1, 2, 3].
  17. [2025-11-15 19:19:53,163]::[InvokeAI]::INFO --> Invoke running on http://127.0.0.1:9090 (Press CTRL+C to quit)
  18. [2025-11-15 19:20:12,725]::[InvokeAI]::INFO --> Executing queue item 8, session 017d973a-7954-4d94-89fc-adacb5dd692a
  19. `torch_dtype` is deprecated! Use `dtype` instead!
  20. [2025-11-15 19:20:13,389]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '02f53758-36bd-4dc6-afc5-c4dc431b07dd:text_encoder' (CLIPTextModel) onto cuda device in 0.43s. Total model size: 234.72MB, VRAM: 234.72MB (100.0%)
  21. [2025-11-15 19:20:13,430]::[ModelManagerService]::INFO --> [MODEL CACHE] Loaded model '02f53758-36bd-4dc6-afc5-c4dc431b07dd:tokenizer' (CLIPTokenizer) onto cuda device in 0.00s. Total model size: 0.00MB, VRAM: 0.00MB (0.0%)
  22. [2025-11-15 19:20:13,445]::[InvokeAI]::ERROR --> Error while invoking session 017d973a-7954-4d94-89fc-adacb5dd692a, invocation 1e5452a0-bb3c-4489-9e4f-587c529fe68c (sdxl_compel_prompt): HIP error: invalid device function
  23. HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
  24. For debugging consider passing AMD_SERIALIZE_KERNEL=3
  25. Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.
  26.  
  27. [2025-11-15 19:20:13,445]::[InvokeAI]::ERROR --> Traceback (most recent call last):
  28. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/invokeai/app/services/session_processor/session_processor_default.py", line 130, in run_node
  29. output = invocation.invoke_internal(context=context, services=self._services)
  30. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  31. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/invokeai/app/invocations/baseinvocation.py", line 244, in invoke_internal
  32. output = self.invoke(context)
  33. ^^^^^^^^^^^^^^^^^^^^
  34. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
  35. return func(*args, **kwargs)
  36. ^^^^^^^^^^^^^^^^^^^^^
  37. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/invokeai/app/invocations/compel.py", line 280, in invoke
  38. c1, c1_pooled = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True)
  39. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  40. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/invokeai/app/invocations/compel.py", line 226, in run_clip_compel
  41. c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
  42. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  43. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/compel.py", line 190, in build_conditioning_tensor_for_conjunction
  44. this_conditioning, this_options = self.build_conditioning_tensor_for_prompt_object(p)
  45. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  46. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/compel.py", line 222, in build_conditioning_tensor_for_prompt_object
  47. return self._get_conditioning_for_flattened_prompt(prompt), {}
  48. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  49. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/compel.py", line 285, in _get_conditioning_for_flattened_prompt
  50. return self.conditioning_provider.get_embeddings_for_weighted_prompt_fragments(
  51. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  52. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 129, in get_embeddings_for_weighted_prompt_fragments
  53. base_embedding = self.build_weighted_embedding_tensor(tokens, per_token_weights, mask, device=device)
  54. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  55. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 409, in build_weighted_embedding_tensor
  56. empty_z = self._encode_token_ids_to_embeddings(empty_token_ids)
  57. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  58. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/compel/embeddings_provider.py", line 442, in _encode_token_ids_to_embeddings
  59. text_encoder_output = self.text_encoder(token_ids,
  60. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  61. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
  62. return self._call_impl(*args, **kwargs)
  63. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  64. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
  65. return forward_call(*args, **kwargs)
  66. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  67. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/transformers/utils/generic.py", line 918, in wrapper
  68. output = func(self, *args, **kwargs)
  69. ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  70. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 706, in forward
  71. return self.text_model(
  72. ^^^^^^^^^^^^^^^^
  73. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
  74. return self._call_impl(*args, **kwargs)
  75. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  76. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
  77. return forward_call(*args, **kwargs)
  78. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  79. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 603, in forward
  80. hidden_states = self.embeddings(input_ids=input_ids, position_ids=position_ids)
  81. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  82. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
  83. return self._call_impl(*args, **kwargs)
  84. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  85. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
  86. return forward_call(*args, **kwargs)
  87. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  88. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/transformers/models/clip/modeling_clip.py", line 246, in forward
  89. inputs_embeds = self.token_embedding(input_ids)
  90. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  91. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
  92. return self._call_impl(*args, **kwargs)
  93. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  94. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
  95. return forward_call(*args, **kwargs)
  96. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  97. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/invokeai/backend/model_manager/load/model_cache/torch_module_autocast/custom_modules/custom_embedding.py", line 29, in forward
  98. return super().forward(input)
  99. ^^^^^^^^^^^^^^^^^^^^^^
  100. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/modules/sparse.py", line 190, in forward
  101. return F.embedding(
  102. ^^^^^^^^^^^^
  103. File "/mnt/Linux Files/InvokeAI/.venv/lib/python3.12/site-packages/torch/nn/functional.py", line 2551, in embedding
  104. return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
  105. ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  106. RuntimeError: HIP error: invalid device function
  107. HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
  108. For debugging consider passing AMD_SERIALIZE_KERNEL=3
  109. Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.
  110.  
  111.  
  112. [2025-11-15 19:20:13,451]::[InvokeAI]::INFO --> Graph stats: 017d973a-7954-4d94-89fc-adacb5dd692a
  113. Node Calls Seconds VRAM Used
  114. sdxl_model_loader 1 0.005s 0.000G
  115. sdxl_compel_prompt 2 0.705s 0.237G
  116. collect 1 0.001s 0.000G
  117. string 1 0.000s 0.000G
  118. TOTAL GRAPH EXECUTION TIME: 0.711s
  119. TOTAL GRAPH WALL TIME: 0.713s
  120. RAM used by InvokeAI process: 1.55G (+0.516G)
  121. RAM used to load models: 1.52G
  122. VRAM in use: 0.237G
  123. RAM cache statistics:
  124. Model cache hits: 4
  125. Model cache misses: 3
  126. Models cached: 3
  127. Models cleared from cache: 0
  128. Cache high water mark: 1.52/0.00G
  129.  
  130.  
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!