load_inline should always recompile a kernel if it failed #119206
Labels
module: cpp-extensions
Related to torch.utils.cpp_extension
triaged
This issue has been looked at a team member, and triaged and prioritized into an appropriate module
馃悰 Describe the bug
Repro in the real world here https://github.com/cuda-mode/lectures/blob/main/lecture3/pmpp.ipynb
If you try to load a kernel without ninja the load will fail but then if you
pip install ninja
and try to reload the kernel it will still fail. So instead I've noticed users are adding an;
in source code to force a recompilation but that doesn't seem greatVersions
A standard google colab instance
cc @malfet @zou3519
The text was updated successfully, but these errors were encountered: