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] InstanceNorm2d -> Reciprocal -> Conv2d causing mismatch between tvm and ONNXRuntime
- [Bug] HardSigmoid returns 1.0 for NaN input (ONNX model mismatch with ORT)
- [Bug] Minor output drift from ONNXRuntime in GroupNorm → Tanh → BatchNorm → Conv2d chain
- [Bug] TVM result diverges from reference
- Fixing generated sample init pop size
- [Bug] Error occurred during tvm compilation
- KVCache Sequence Padding
- [bug/feature][relax.frontend.torch] from_exported_program rejects randn.default (blocks repro that stresses advanced-indexing write + tuple output)
- [feature][relax.frontend.torch] Missing coverage for STFT+RNN pipeline: 'rnn_tanh.input', 'real.default', 'imag.default', 'unfold.default', 'fft_fft.default' in from_exported_program
- [Bug] [relax][torch] from_exported_program segfault with exported MHA using eq(0)/expand mask + in-place masked_fill_ (get_attr lifting warning from PyTorch)
- Docs
- Python not yet supported