thuml/depyf
depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
This tool helps machine learning researchers and engineers understand what's happening inside PyTorch's `torch.compile` when it optimizes their models. It takes your PyTorch code using `torch.compile` and outputs detailed, human-readable Python code, bytecode, and graph representations, allowing you to debug and tune your model's performance. It is designed for those who work with PyTorch and want to optimize their model's execution.
794 stars. Used by 2 other packages. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher struggling to understand or debug performance issues with your PyTorch models after applying `torch.compile`.
Not ideal if you are not using PyTorch's `torch.compile` feature, or if you are not actively trying to optimize or debug the low-level execution of your PyTorch models.
Stars
794
Forks
27
Language
Python
License
MIT
Category
Last pushed
Oct 13, 2025
Commits (30d)
0
Dependencies
2
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/depyf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)