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 printer emits type annotation that the parser cannot read back (TupleType of PrimType)
- [Bug] FuseTransposeMatmul crashes with AttributeError: 'TupleType' object has no attribute 'dtype' when the transposed operand is used outside the pattern
- [FIX][LLVM] Support bool Add/Sub/Mul in LLVM codegen
- [Bug] LLVM codegen aborts on arithmetic over "bool" buffers (Add/Sub/Mul)
- [Bugfix][Relax] Fix float16 batch norm folding
- [Fix][Relax][ONNX] Support runtime shape tensors in Reshape
- [Metal] Compile MSL source with the highest language version the OS supports
- [FIX][ROCm] Use HIP for device existence checks
- MergeCompositeFunctions aborts when main is not the only Relax function
- [Bug][Relax] FoldBatchnormToConv2D ignores disabled scale and center attributes
- Docs
- Python not yet supported