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
- [Docs] Switch documentation theme to sphinx-book-theme
- [Relax][ONNX] Support 3D AffineGrid
- [RESULT][VOTE] Release Apache TVM v0.25.0
- # [Performance] `nn.pad` reflect/replicate ~1.5x slower than needed since v0.21 (nested `if_then_else` boundary index)
- [RUNTIME][FFI][RELAX] Add vm.builtin.shape_to_tensor builtin
- [Relax][PyTorch] Add rnn_tanh.input converter
- [Relax][Frontend][ONNX] Add support for Pad mode="wrap" for opset 19
- [Relax][TFLite] Add remaining operator tests and reverse_sequence op
- [Runtime][WebGPU] Add prerequisites for Gemma 4 E2B WebGPU execution
- [Web] Improve large tensor loading in wasm runtime
- Docs
- Python not yet supported