deepspeedai / deepspeedai/DeepSpeed
[REQUEST] FlashAttention support for LLM inference
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
Is there any plan to support FlashAttention for LLM inference?
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
The issue provides no files, tests, or entry points. Start by clarifying the intended FlashAttention support and reviewing the existing LLM inference path and attention implementation. Done criteria are not specified, so scope and validation would need to be agreed before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100