-
Notifications
You must be signed in to change notification settings - Fork 103
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Command '['C:\\Program Files (x86)\\Microsoft Visual Studio\\2019\\BuildTools\\VC\\Tools\\MSVC\\14.29.30133\\bin\\Hostx64\\x64\\cl.EXE' #1
Comments
I think there may be a line missing in this file: try:
from flash_attn.flash_attn_interface import flash_attn_varlen_func
except ImportError:
flash_attn_varlen_func = None
sageattn_varlen_func = None #THE MISSING LINE
try:
from sageattention import sageattn_varlen
@torch.compiler.disable()
def sageattn_varlen_func( |
ok i will give a shot |
I just realized that your issue may be different from the one I was having. The error you got seems to be related to the CUDA utilities and triton. You could maybe try removing and adding triton: pip uninstall triton sageattention -y
pip install triton --no-cache-dir
pip install sageattention --no-cache-dir |
ok,thanks |
It doesn't currently work without flash_attn or sageattention, both are somewhat challenging to install on Windows. This error is from incomplete or missing Triton installation that sageattention uses. |
Use the manual from purz. https://purz.notion.site/Get-Windows-Triton-working-for-Mochi-6a0c055e21c84cfba7f1dd628e624e97 |
Only 3.11 and 3.12 Python versions are available
Extract the include and libs folders and place them under ComfyUI\python_ embedded This can work normally for me |
IP2V - Experimental implementation based on Kijai Nodes, Initial Commit
ComfyUI Error Report
Error Details
1\AppData\Local\Temp\tmpnpldo08z\main.c', '/nologo', '/O2', '/LD', '/wd4819', '/ID:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\include', '/IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include', '/IC:\Users\ADMINI1\AppData\Local\Temp\tmpnpldo08z', '/ID:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Include', '/IC:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\include', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\shared', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\ucrt', '/IC:\Program Files (x86)\Windows Kits\10\Include\10.0.19041.0\um', '/link', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\Lib\site-packages\triton\backends\nvidia\lib', '/LIBPATH:C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\lib\x64', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:C:\Python311\libs', '/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\lib\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\ucrt\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\um\x64', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:D:\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\python_embeded\libs', '/LIBPATH:C:\Python311\libs', '/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30133\lib\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\ucrt\x64', '/LIBPATH:C:\Program Files (x86)\Windows Kits\10\Lib\10.0.19041.0\um\x64', 'cuda.lib', '/OUT:C:\Users\ADMINI~1\AppData\Local\Temp\tmpnpldo08z\cuda_utils.cp311-win_amd64.pyd']' returned non-zero exit status 2.Stack Trace
System Information
Devices
Logs
The text was updated successfully, but these errors were encountered: