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 ONNX front]ONNX frontend import failed with shape graph Concat error
- [Bug][Relax] Import failures on PaddleOCR and FasterRCNN-style models: Squeeze axes, shape Gather, and dynamic TopK
- [REFACTOR][CUDA] Clarify CUDA codegen flow
- [Bug] [Relax] `InternalError: Divide by zero` when compiling a `reshape` that yields a 0-sized dimension
- [Runtime][WebGPU] Add prerequisites for Gemma 4 E2B WebGPU execution
- [Web] Improve large tensor loading in wasm runtime
- [Relax][Frontend][ONNX] Fix Resize coordinate error with non-integer scales
- [Bug][Relax] `nn.conv{1,2,3}d_transpose` legalize silently bails for unsupported `dilation` / `data_layout`, causing opaque VM-codegen crash
- [Bug] Relax ONNX Min and ArgMin mishandle NaN semantics
- [Bug] layer_norm` Relax/TIR module crashes the process on Windows
- Docs
- Python not yet supported