deepspeedai / deepspeedai/DeepSpeed
SparseSelfAttention doesn't work with max_seq_length=4096
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
The error we occurred is shown above. The SparseSelfAttention doesn't work with max_seq_length=4096.
https://github.com/microsoft/DeepSpeed/blob/master/deepspeed/ops/sparse_attention/sparse_self_attention.py#L27
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 with deepspeed/ops/sparse_attention/sparse_self_attention.py at line 27 and reproduce the reported failure using max_seq_length=4096. Inspect the error shown in the attached image and trace how that value is handled by SparseSelfAttention. Done means the configuration no longer produces the reported error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100