[QST] Modifyinf a conv2d kernel and using it with python and pytorch
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 10.5k
- Forks
- 2.1k
- Avg merge
- 3d 11h
- Merged PRs (30d)
- 7
Description
What is your question?
Hi, I aim to modify a convolution2d kernel to use it in Python with Pytorch later while performing the inference of a neural network model as Resnet50.
Basically, it is to change the base convolution kernel to add an extra parameter that modifies the weights.
I would like to know which is the easiest way to make this change, if on the kernel implementation itself in C++ and then also if I should use Cutlass with Python or Pycutlass. I am still determining precisely what is the difference between them and which one can help me more in my goal. Apparently, it seems that Pycutlass is deprecated; I don't know if this is confirmed.
Thanks
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by comparing the CUTLASS C++ kernel approach with the Python, PyTorch, and PyCUTLASS options named in the question. Determine which integration path supports adding a parameter that modifies convolution weights during ResNet50 inference, and confirm whether PyCUTLASS is deprecated. The issue provides no file or test entry point, and the question remains unanswered.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100