Accelerating Blockwise Parallel Language Models with Draft Refinement

Taehyeon Kim, A. Suresh, Kishore Papineni, Michael Riley, Sanjiv Kumar +1 more
2/3/2026

No confident code implementation found for this paper.

DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{kim2026accelerating,
  title  = {Accelerating Blockwise Parallel Language Models with Draft Refinement},
  author = {Taehyeon Kim and A. Suresh and Kishore Papineni and Michael Riley and Sanjiv Kumar and Adrian Benton},
  year   = {2026},
  doi    = {10.52202/079017-1081},
  url    = {https://doi.org/10.52202/079017-1081},
  journal = {NEURIPS 2024 2024}
}

Discussion