Flash Attention Issue
Hi, I'm attempting to implement this model on my local server and keep encountering flash attention errors. I have confirmed that Cuda is running properly.
(MiniCPM-V) D:\ML model\MiniCPM-V>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Fri_Jun_14_16:44:19_Pacific_Daylight_Time_2024
Cuda compilation tools, release 12.6, V12.6.20
Build cuda_12.6.r12.6/compiler.34431801_0
Installing build dependencies: finished with status 'done'
Getting requirements to build wheel: started
Getting requirements to build wheel: finished with status 'error'
Note: you may need to restart the kernel to use updated packages.
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...
error: subprocess-exited-with-error
Γ Getting requirements to build wheel did not run successfully.
β exit code: 1
β°β> [25 lines of output]
Traceback (most recent call last):
File "c:\Users\munee\anaconda3\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 353, in
main()
File "c:\Users\munee\anaconda3\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 335, in main
json_out['return_val'] = hook(**hook_input['kwargs'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\Users\munee\anaconda3\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 118, in get_requires_for_build_wheel
return hook(config_settings)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\munee\AppData\Local\Temp\pip-build-env-wjq4vueo\overlay\Lib\site-packages\setuptools\build_meta.py", line 332, in get_requires_for_build_wheel
return self._get_build_requires(config_settings, requirements=[])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\munee\AppData\Local\Temp\pip-build-env-wjq4vueo\overlay\Lib\site-packages\setuptools\build_meta.py", line 302, in _get_build_requires
self.run_setup()
File "C:\Users\munee\AppData\Local\Temp\pip-build-env-wjq4vueo\overlay\Lib\site-packages\setuptools\build_meta.py", line 318, in run_setup
exec(code, locals())
File "", line 25, in
File "C:\Users\munee\AppData\Local\Temp\pip-build-env-wjq4vueo\overlay\Lib\site-packages\Cython\Build\Dependencies.py", line 1010, in cythonize
module_list, module_metadata = create_extension_list(
^^^^^^^^^^^^^^^^^^^^^^
...
β exit code: 1
β°β> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip.
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings..
please provide the running code and error message about flash attention