tvm
https://github.com/apache/tvm
Python
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported3 Subscribers
Add a CodeTriage badge to tvm
Help out
- Issues
- [Bug][Relax] FoldBatchnormToConv2D crashes on float16 BatchNorm constants
- [Bugfix][Relax] Fix IOHW batch norm folding
- [Bugfix][Relax] Skip training batch norm folding
- [Bug] TIRx/CUDA: an annotated host-level scalar (`c: T.float32 = ...`) is allocated on the device and then written from the host (SIGSEGV)
- [Bug][Relax] FoldBatchnormToConv2D changes semantics for training BatchNorm
- [Bug][Relax] FoldBatchnormToConv2D crashes for the documented IOHW kernel layout
- [Fix][Relax][Frontend][Torch] Apply the scale and input_scale arguments of aten.elu
- [Bug][Relax][ONNX] Training BatchNormalization uses the opposite momentum convention
- [Bug][Relax][ONNX] LayerNormalization replaces optional Mean and InvStdDev outputs with scalar zeros
- [Bug][Relax][ONNX] ConvTranspose ignores output_shape
- Docs
- Python not yet supported