why so many kernels use cubin? fully open-source?
Open
Nobody has claimed this yet.
Customized kernels
question
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
As the new show:
[03/22] TensorRT-LLM is now fully open-source, with developments moved to GitHub!
BUT，why so many kernels use cubin? like this: cubin
Thank you!
Contributor guide
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 reviewing the linked cpp/tensorrt_llm/kernels/trtllmGenKernels/gemmGatedAct/trtllmGen_gatedAct_export/cubins directory and the repository description. Determine why these kernels are distributed as cubin files and whether that is consistent with the project's fully open-source claim; done means providing a clear explanation.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai-infra-agents, performance
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100