mirror of
https://github.com/open-webui/open-webui.git
synced 2026-06-08 18:17:14 -05:00
issue: Attaching file to a prompt produces a CUDA error #5073
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#5073
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @Nexxsys on GitHub (May 6, 2025).
Check Existing Issues
Installation Method
Docker
Open WebUI Version
v0.6.6 - 2025-05-05
Ollama Version (if applicable)
3.2:Latest
Operating System
Linux Mint 12
Browser (if applicable)
Brave
Confirmation
README.md.Expected Behavior
File is attached with no error.
Actual Behavior
Attaching a file to a prompt produces this error: CUDA error: no kernel image is available for execution on the device 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_DSAto enable device-side assertions.Steps to Reproduce
At the prompt, click the plus sign Upload Files, and select any file of any type to produce the error
Logs & Screenshots
File "/usr/local/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 1080, in forward
embedding_output = self.embeddings(
└ BertModel(
(embeddings): BertEmbeddings(
(word_embeddings): Embedding(30522, 384, padding_idx=0)
(position_embeddin...
File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
│ │ │ └
│ │ └ ()
│ └ <function Module._call_impl at 0x7d591af7c9a0>
└ BertEmbeddings(
(word_embeddings): Embedding(30522, 384, padding_idx=0)
(position_embeddings): Embedding(512, 384)
(tok...
File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
│ │ └
│ └ ()
└ <bound method BertEmbeddings.forward of BertEmbeddings(
(word_embeddings): Embedding(30522, 384, padding_idx=0)
(position...
File "/usr/local/lib/python3.11/site-packages/transformers/models/bert/modeling_bert.py", line 211, in forward
inputs_embeds = self.word_embeddings(input_ids)
│ └
└ BertEmbeddings(
(word_embeddings): Embedding(30522, 384, padding_idx=0)
(position_embeddings): Embedding(512, 384)
(tok...
File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
│ │ │ └ {}
│ │ └
│ └ <function Module._call_impl at 0x7d591af7c9a0>
└ Embedding(30522, 384, padding_idx=0)
File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
return forward_call(*args, **kwargs)
│ │ └ {}
│ └
└ <bound method Embedding.forward of Embedding(30522, 384, padding_idx=0)>
File "/usr/local/lib/python3.11/site-packages/torch/nn/modules/sparse.py", line 190, in forward
return F.embedding(
│ └ <function embedding at 0x7d5915bb6700>
└ <module 'torch.nn.functional' from '/usr/local/lib/python3.11/site-packages/torch/nn/functional.py'>
File "/usr/local/lib/python3.11/site-packages/torch/nn/functional.py", line 2551, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
│ │ │ │ │ │ └ False
│ │ │ │ │ └ False
│ │ │ │ └ 0
│ │ │ └
│ │ └
│ └ <built-in method embedding of type object at 0x7d5a208d8f80>
└ <module 'torch' from '/usr/local/lib/python3.11/site-packages/torch/init.py'>
RuntimeError: CUDA error: no kernel image is available for execution on the device
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_DSAto enable device-side assertions.During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x7d5a31bac860>
└ <WorkerThread(AnyIO worker thread, started 137818412148416)>
File "/usr/local/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function WorkerThread.run at 0x7d58851c6200>
└ <WorkerThread(AnyIO worker thread, started 137818412148416)>
File "/usr/local/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
result = context.run(func, *args)
│ │ │ └ ()
│ │ └ functools.partial(<function upload_file at 0x7d58f0bc8400>, user=UserModel(id='60b2ead4-73fa-43bc-a0ff-8538523c50f7', name='T...
│ └ <method 'run' of '_contextvars.Context' objects>
└ <_contextvars.Context object at 0x7d5885172a80>
Additional Information
NVIDIA-SMI 550.144.03 Driver Version: 550.144.03 CUDA Version: 12.4