400-bug-report.yml 3.7 KB

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071
  1. name: 🐛 Bug report
  2. description: Raise an issue here if you find a bug.
  3. title: "[Bug]: "
  4. labels: ["bug"]
  5. body:
  6. - type: markdown
  7. attributes:
  8. value: >
  9. #### Before submitting an issue, please make sure the issue hasn't been already addressed by searching through [the existing and past issues](https://github.com/PygmalionAI/aphrodite-engine/issues?q=is%3Aissue+sort%3Acreated-desc+).
  10. - type: textarea
  11. attributes:
  12. label: Your current environment
  13. description: |
  14. Please run the following and paste the output below.
  15. ```sh
  16. wget https://raw.githubusercontent.com/PygmalionAI/aphrodite-engine/main/env.py
  17. # For security purposes, please check the contents of env.py before running it.
  18. python env.py
  19. ```
  20. value: |
  21. <details>
  22. <summary>The output of `python env.py`</summary>
  23. ```text
  24. Your output of `python env.py` here
  25. ```
  26. </details>
  27. validations:
  28. required: true
  29. - type: textarea
  30. attributes:
  31. label: Model Input Dumps
  32. description: |
  33. If you are facing crashing due to illegal memory access or other issues with model execution, Aphrodite may dump the problematic input of the model. In this case, you will see the message `Error in model execution (input dumped to /tmp/err_xxx.pkl)`. If you see this message, please zip the file (because GitHub doesn't support .pkl file format) and upload it here. This will help us to reproduce the issue and facilitate the debugging process.
  34. placeholder: |
  35. Upload the dumped input file.
  36. validations:
  37. required: false
  38. - type: textarea
  39. attributes:
  40. label: 🐛 Describe the bug
  41. description: |
  42. Please provide a clear and concise description of what the bug is.
  43. If relevant, add a minimal example so that we can reproduce the error by running the code. It is very important for the snippet to be as succinct (minimal) as possible, so please take time to trim down any irrelevant code to help us debug efficiently. We are going to copy-paste your code and we expect to get the same result as you did: avoid any external data, and include the relevant imports, etc. For example:
  44. ```python
  45. # All necessary imports at the beginning
  46. import torch
  47. # A succinct reproducing example trimmed down to the essential parts:
  48. t = torch.rand(5, 10) # Note: the bug is here, we should pass requires_grad=True
  49. t.sum().backward()
  50. ```
  51. If the code is too long (hopefully, it isn't), feel free to put it in a public gist and link it in the issue: https://gist.github.com.
  52. Please also paste or describe the results you observe instead of the expected results. If you observe an error, please paste the error message including the **full** traceback of the exception. It may be relevant to wrap error messages in ```` ```triple quotes blocks``` ````.
  53. placeholder: |
  54. A clear and concise description of what the bug is.
  55. ```python
  56. # Sample code to reproduce the problem
  57. ```
  58. ```
  59. Your error message with the FULL traceback.
  60. ```
  61. validations:
  62. required: true
  63. - type: markdown
  64. attributes:
  65. value: >
  66. ⚠️ Please separate bugs of `transformers` implementation or usage from `aphrodite` bugs. If you think anything is wrong with the models' output:
  67. - Try the same model on transformers. If the issue persists, submit your problem to [their issues](https://github.com/huggingface/transformers/issues?q=is%3Aissue+is%3Aopen+sort%3Aupdated-desc).
  68. - If the error only appears in Aphrodite, please provide the detailed script of how you run `transformers` and `aphrodite` tests, also highlight the difference and what you expect.
  69. Thanks for contributing 🎉~