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
- [WIP] GNN Cost Model addition
- [Bug] Segmentation fault while importing tvm
- [Relax] Expose BlockBuilder's Analyzer instance in Python
- [Bug] Torchvision convnext Core Dump and the engine file larger than 3GB
- [Bug] CUDA_ERROR_INVALID_IMAGE when deploying ResNet18 model to Jetson AGX Orin 32GB using TVM
- [BugFix][CUDA] Increase FloatImm precision when printing 64 bit values in CUDA codegen
- [Bug] [Relax] Build fails when applying `dlight.gpu.GeneralReduction` to `R.nn.group_norm` with dynamic shapes and `R.reshape`
- [Bug] Check failed: (::tvm::runtime::IsContiguous(tensor->dl_tensor)) is false: DLManagedTensor must be contiguous.
- [COLLAGE][BYOC][ADRENO] Integrate byoc preprocess in collage and benchmark
- [GRAPH RT] Additional API support
- Docs
- Python not yet supported