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
- [Bug] onnx quantize op support MatMulIntegerToFloat QLinearConv
- [Bug] Error opening FastRPC channel
- [Relax][Bug] CodeGenVM cannot handle this intrinsic tensor_to_shape
- [Tracking Issue] Remove `distutils` dependency from the codebase
- [Bug] [Relax] [TIR] FuseOps and FuseTIR cannot fuse no-op reshape into other `PrimFunc`s, nor can they eliminate that
- [KVCache] PagedKVCache Quantization
- [Bug] Building for qualcomm hexagon dsp V66 architeture
- [TVMScript] Print small constant arrays as in-line R.const
- [BUG]: Relay.transform.FoldScaleAxis() Error in folding the SqueezeExcitation structure of mobilenetv3.
- TVM performs convolution time performance issues.
- Docs
- Python not yet supported