deepspeedai / deepspeedai/DeepSpeed

Question about the definitions in block sparse attention

Open
#519 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
43.1k
Forks
5k
Avg merge
4d 15h
Merged PRs (30d)
112

Description

Hi, I have some question regarding the block sparse attention.

If I understand the description of API correctly, block is the block size (i.e., number of tokens in a block) while num_local_blocks denotes the number of blocks (#tokens_per_window = block * num_local_blocks) in a local window. So no matter which value (unidirectional or bidirectional) I choose for attention, the tokens within a block will attend each other?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file, test, or entry point is named. Start by locating the block sparse attention API documentation and implementation, then verify the meanings of block, num_local_blocks, and attention. Done means the documentation clearly answers whether tokens within a block attend each other under both attention modes.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.