[GH-ISSUE #9] RuntimeError: cannot reshape tensor of 0 elements into shape [1, 0, -1, 128] #7

Open
opened 2026-10-26 21:09:59 +00:00 by bsakaguchi · 3 comments
Owner

Originally created by @YoungSeng on GitHub (Dec 16, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/9

I'm encountering a RuntimeError when trying to run a script with the DeepSeek-VL2-tiny model for image and language processing. Specifically, the error occurs during the forward pass in the generate method of the vl_gpt.language object.

Error Message:

Traceback (most recent call last):
  File "/home/yiqiao/Desktop/DeepSeek-VL2/mydemo.py", line 57, in <module>
    outputs = vl_gpt.language.generate(
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/generation/utils.py", line 2252, in generate
    result = self._sample(
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/generation/utils.py", line 3251, in _sample
    outputs = self(**model_inputs, return_dict=True)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1723, in forward
    outputs = self.model(
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1592, in forward
    layer_outputs = decoder_layer(
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1306, in forward
    hidden_states, self_attn_weights, present_key_value = self.self_attn(
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 309, in forward
    query_states = query_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2)
RuntimeError: cannot reshape tensor of 0 elements into shape [1, 0, -1, 128] because the unspecified dimension size -1 can be any value and is ambiguous

Environment:

torch                             2.5.1+cu121
torchaudio                        2.5.1+cu121
torchvision                       0.20.1+cu121
Originally created by @YoungSeng on GitHub (Dec 16, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL2/issues/9 I'm encountering a `RuntimeError` when trying to run a script with the `DeepSeek-VL2-tiny` model for image and language processing. Specifically, the error occurs during the forward pass in the `generate` method of the `vl_gpt.language` object. ### Error Message: ``` Traceback (most recent call last): File "/home/yiqiao/Desktop/DeepSeek-VL2/mydemo.py", line 57, in <module> outputs = vl_gpt.language.generate( File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/generation/utils.py", line 2252, in generate result = self._sample( File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/generation/utils.py", line 3251, in _sample outputs = self(**model_inputs, return_dict=True) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1723, in forward outputs = self.model( File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1592, in forward layer_outputs = decoder_layer( File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "/home/yiqiao/Desktop/DeepSeek-VL2/deepseek_vl/models/modeling_deepseek.py", line 1306, in forward hidden_states, self_attn_weights, present_key_value = self.self_attn( File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl return forward_call(*args, **kwargs) File "/home/yiqiao/miniconda3/envs/vita/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py", line 309, in forward query_states = query_states.view(bsz, q_len, -1, self.head_dim).transpose(1, 2) RuntimeError: cannot reshape tensor of 0 elements into shape [1, 0, -1, 128] because the unspecified dimension size -1 can be any value and is ambiguous ``` ### Environment: ``` torch 2.5.1+cu121 torchaudio 2.5.1+cu121 torchvision 0.20.1+cu121 ```
Author
Owner

@robinren03 commented on GitHub (Dec 17, 2024):

see https://github.com/deepseek-ai/DeepSeek-VL2/issues/4#issuecomment-2545441738

<!-- gh-comment-id:2547553021 --> @robinren03 commented on GitHub (Dec 17, 2024): see https://github.com/deepseek-ai/DeepSeek-VL2/issues/4#issuecomment-2545441738
Author
Owner

@NB-wo commented on GitHub (Dec 25, 2024):

see #4 (comment)

I've tried but I get the same error

<!-- gh-comment-id:2561707316 --> @NB-wo commented on GitHub (Dec 25, 2024): > see [#4 (comment)](https://github.com/deepseek-ai/DeepSeek-VL2/issues/4#issuecomment-2545441738) I've tried but I get the same error
Author
Owner

@ccx1997 commented on GitHub (Dec 30, 2024):

Try https://github.com/deepseek-ai/DeepSeek-VL2/issues/4#issuecomment-2562709343

<!-- gh-comment-id:2565294210 --> @ccx1997 commented on GitHub (Dec 30, 2024): Try https://github.com/deepseek-ai/DeepSeek-VL2/issues/4#issuecomment-2562709343
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-VL2#7
No description provided.