NVIDIA/cuda-tile
View on GitHubCUDA Tile IR is an MLIR-based intermediate representation and compiler infrastructure for CUDA kernel optimization, focusing on tile-based computation patterns and optimizations targeting NVIDIA tensor core units.
- Stars
- 1k
- Forks
- 89
- Open beginner issues
- 0
- Indexed issues
- 5
- Dominant language
- C++
- License
- No license data
- Last GitHub push
- Sep 10, 2026
- Latest indexed
- Sep 19, 2026
- Contributing guide
- No contributing guide
- Code of conduct
- No code of conduct
- Beginner labels
- No beginner labels indexed
- PR merge metrics
- No merged PRs in 30d
5 open issues indexed
Loading issues
-
bug
Difficulty 4/5 3-5 days Newbie friendliness 52/100
-
Host SIGSEGV in cuLaunchKernel when cuModuleUnload runs concurrently, with Tile IR modules only. Openbug
Difficulty 4/5 3-5 days Newbie friendliness 38/100
-
enhancement
Difficulty 5/5 Over a week Newbie friendliness 35/100
-
enhancement
NVIDIA/cuda-tile#21 · 3 comments · 1 reaction · 1 assignee ·
-
enhancement