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] [RISC-V RVV] sigmoid operator slower with vector extension
- [Bug] [RISC-V RVV] softmax operator shows suboptimal vectorization
- [Bug] Issue: [RISC-V RVV] negative operator shows performance degradation
- [Bug] [RISC-V RVV] max_pool2d operator shows minor performance regression
- [Bug] [RISC-V RVV] cos operator shows slight performance degradation
- [Tracking Issue] Dogfood `tvm-ffi-stubgen` in TVM Codebase
- [Bug] Segfault in `tvm.compile (Relax, target=llvm)` during TIR pass `InjectPTXLDG32` / `PTXRewriter::VisitStmt_(BufferStore)` even though target is CPU-only
- [Bug] Segfault in `tvm.compile` on **LLVM (CPU) target** when `tir.ptx_ldg32=1`: unexpectedly runs `tir::transform::InjectPTXLDG32` / `PTXRewriter` and crashes in `BufferStore`
- [Bug] Segfault in LLVM COFFOptTable when combining TVM CUDA target with PyTorch Lightning + torchmetrics in the same process
- [Bug] Segmentation fault when using TVM together with `transformers` (flan-t5-base + bfloat16 + `use_cache=True`)
- Docs
- Python not yet supported