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] DecomposeOpsForTraining rejects BatchNorm with a valid negative axis
- [Bug][Relax] LambdaLift crashes when a captured local function is called through an alias
- [Bug] Gradient rejects a function that returns a tuple bound to a Var, regardless of target_index
- [Bug] MergeCompositeFunctions fails on a well-formed module when main is not the only Relax function
- [Fix][Relax][ONNX] Honor detect_negative and detect_positive in IsInf
- [Bugfix][Relax] Avoid dangling globals in AllocateWorkspace
- [Relax] Fix FoldConstant crash on data-dependent reshape with unknown shape
- [Bug] AllocateWorkspace returns an ill-formed module with a dangling GlobalVar
- [Fix][Relax][Frontend][TFLite] Match quantized AvgPool rounding
- [Fix][Relax] Skip PrimType arguments during callsite specialization
- Docs
- Python not yet supported