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 supported2 Subscribers
Add a CodeTriage badge to tvm
Help out
- Issues
- [MetaSchedule]Fix the bug when loading database_tuning_record.json if there is pad_einsum primitive
- [Bug] [Relax] [LambdaLift] Argument type mismatch: expected R.Tensor, given R.Object
- [Relay][Frontend][Torch] support `torch.index_fill_`
- [Bug] [CodeGen] InternalError: Check failed: (is_zero(op->min)) is false during CodeGen
- [Bug] [TIR] Variable is not defined in the environment IndexError when compiling TIR that looks 'correct'
- [Bug] [tir] tir.LowerIntrin check failed additional_info.size() == new_size (34 vs. 33)
- [Bug] InternalError: Register Index Out of Bounds After LambdaLift Transformation with Nested Function in Relax VM Execution
- [Bug] Flaky Behavior in Relax VM Execution: "ValueError: negative dimensions are not allowed" and "Floating point exception (core dumped)"
- [Bug] Data Type Mismatch (int64 vs int32) in T.match_buffer when Working with Scalar Buffers in TIR
- Added bit-serial operators for AArch64
- Docs
- Python not yet supported