How to use block_sparse in tensorrt_llm.layers.attention.Attention
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
Hi there,
I want to evaluate the performance of block_sparse attention (should be in tensorrt_llm.layers.attention.Attention). How is it implemented? Is there any tutorial for it?
I also noticed that tensorrt_llm.functional.gpt_attention has parameters for block_sparse, but I did not find anywhere that has an example for it.
Thanks!
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 reading tensorrt_llm.layers.attention.Attention and tensorrt_llm.functional.gpt_attention, focusing on their block_sparse parameters and how they are used. Document the implementation, usage steps, and a tutorial or example that lets users evaluate block-sparse attention performance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100