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
- [Relax][Frontend][TFLite] Read the keys vector byte width in FlexBufferDecoder
- [Fix][Relax] Skip constant LHS in CombineParallelMatmul
- [Bug][S-TIR][Fuzz] `loop_partition` on a reduction loop duplicates the reduction init: the sum keeps only the last partition
- [Fix][S-TIR] Preserve the tail predicate across compute_at after rfactor
- [Bug] [Relax][CUDA] Wrong result for a K=1 matmul chain after AdjustMatmulOrder
- Bump virtualenv from 20.14.1 to 21.14.13 in /docker/python
- [Bug] The source directory /usr/ports/misc/tvm/work/tvm-0.27.0.post1/3rdparty/tvm-ffi does not contain a CMakeLists.txt file.
- [Bug][S-TIR] `compute_at` after `rfactor` drops the tail predicate: wrong sums and out-of-bounds reads
- [Bug][S-TIR][CUDA] `storage_align` + `vectorize` emits misaligned `float4` stores to shared memory
- [Relax] Fix FuseTransposeMatmul crash on rank-1 transpose and reused operand
- Docs
- Python not yet supported