Title: TL1/TL2 codegen fails for any configuration with bm=16 on Windows 11
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 40.3k
- Forks
- 3.7k
- PR merge metrics
- No merged PRs in 30d
Description
When generating TL1/TL2 kernels with bm=16, all configurations fail either during
(1) codegen_tl1.py / codegen_tl2.py execution, or
(2) CMake build (llama-bench build failure).
This happens consistently for all BM/BK settings.
Other block sizes (e.g., bm=32, bm=64, bm=128) work normally.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by running codegen_tl1.py and codegen_tl2.py with bm=16 on Windows 11, then compare the failure with a working bm=32 configuration. Inspect the llama-bench CMake build when code generation succeeds; done means every bm=16 configuration generates and builds successfully.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cmake, cpp, python
- Domain
- build-system, compilers, operating-systems
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100