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] FuseOps can reorder call_tir before symbolic shape binding used in out_ty
- [Bug][Relax][LLVM] scatter_elements with symbolic H/W extents times out during build[Bug]
- [Bug][Relax] CombineParallelMatmul crashes on 1-D matmul boundary cases
- [Bug][Relax] Matmul rewrite passes drop explicit out_dtype and change float32 outputs to float16
- [Bug] [Relax][ONNX] Runtime-shape Reshape import passes TensorType to relax.op.reshape
- [Bug] [Relax][ONNX] Min import fails on symbolic broadcast
- [Bug] [Relax] Static-shape Size/Slice/Reshape hits an uncomputed shape slot
- [Bug] [Relax]Symbolic Flatten/Slice/Cast triggers a duplicate remap assertion
- [Bug][Metal] Metal codegen produces silently-wrong output on a HiFi-GAN-style Relax graph (cosine 0.756 vs LLVM 1.0000)
- [BYOC][oneDNN] Update and maintain oneDNN BYOC integration
- Docs
- Python not yet supported