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][CUDA] topk on large input launches kernel with invalid gridDim.y and fails with CUDA_ERROR_INVALID_VALUE
- [Bug] [Relax][Torch] torch.logical_not on float tensor is lowered to R.logical_not with float dtype and fails LegalizeOps
- [Bug] Relax ONNX Gather mishandles negative indices
- [Bug] Relax ONNX Slice crashes on negative-step empty result
- [Relax][ONNX] Handle empty Slice with negative step
- [Bug] [Relax] `reduce_max` / `reduce_min` silently drop NaN on CUDA — CPU and CUDA produce different results
- [Bug] [Relax] `adaptive_avg_pool2d` compilation crashes on CUDA when output size does not evenly divide input
- [Relax][ONNX] Use ONNX Backend Tests to improve frontend coverage
- [Runtime][Metal] add TVM_METAL_STORAGE_MODE env opt-in for Shared/Managed buffers
- [Bug] model cross compiled with cutlass can't run
- Docs
- Python not yet supported