Block Sparse Attention
MIT HAN LabBlock Sparse Attention is a library of sparse attention kernels from MIT HAN Lab supporting streaming attention at token and block granularity plus block-sparse attention, modified from FlashAttention to reduce the compute and memory cost of long-context LLM inference.
Openness
5 high confidence- license
- BSD-3-Clause(OSI)
- source
- public
- core features withheld
- no
BSD-3-Clause license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated.
- https://api.github.com/repos/mit-han-lab/Block-Sparse-Attention recorded 2026-09-02
Repo metadata for block-sparse-attention's canonical repository - private false, archived false, fork false.
- https://github.com/mit-han-lab/Block-Sparse-Attention/blob/main/LICENSE recorded 2026-10-07
LICENSE body is the verbatim three-clause BSD text, inherited from its FlashAttention base.
- https://github.com/mit-han-lab/Block-Sparse-Attention/blob/main/README.md recorded 2026-10-07
README describes Block Sparse Attention as a library of sparse attention kernels supporting streaming and block-sparse patterns, initially modified from FlashAttention 2.4.2, with no paid tier, enterprise edition or license-gated build beside the published source.
Adoption
1 low confidenceBlock Sparse Attention has no registry package and installs from source, so GitHub stars are the only adoption signal available. A star is not a use.
- https://api.github.com/repos/mit-han-lab/Block-Sparse-Attention recorded 2026-09-02
Repo metadata - stargazers_count = 549 - for mit-han-lab/Block-Sparse-Attention.
Capability
2 medium confidenceBlock Sparse Attention supplies a handful of sparse-pattern attention kernel variants built on top of FlashAttention, rather than the general attention coverage a broader library would need. That narrow kernel set puts it two steps below TensorRT.
- https://github.com/mit-han-lab/Block-Sparse-Attention/blob/main/README.md recorded 2026-10-07
README describes Block Sparse Attention as a library of sparse attention kernels supporting streaming and block-sparse patterns, initially modified from FlashAttention 2.4.2, with no paid tier, enterprise edition or license-gated build beside the published source.
Verified 2026-09-27