Metraipolis › archive › dc_664dfbd90b52

GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring — arXiv:2608.20375

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20375
License (as archived)
CC0-1.0
Archived
2026-10-18T10:18:13.353Z
SHA-256 of the archived text
9dea52a6fb76809b7ca771834314ddc1559145f9ee6748ff00f2a03bdfa0fd7b
Stable URL of this page
https://metraipolis.com/documento/dc_664dfbd90b52

How to cite

GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring — arXiv:2608.20375 — arXiv (en), https://arxiv.org/abs/2608.20375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_664dfbd90b52 (Metraipolis archive dc_664dfbd90b52, sha256 9dea52a6fb76809b7ca771834314ddc1559145f9ee6748ff00f2a03bdfa0fd7b)
BibTeX
@misc{dc664dfbd90b52,
  title = {GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring — arXiv:2608.20375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_664dfbd90b52; sha256 9dea52a6fb76809b7ca771834314ddc1559145f9ee6748ff00f2a03bdfa0fd7b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tree-based speculative decoding raises the mean accepted tokens of standard speculative decoding by verifying multiple draft paths, and existing tree builders typically construct these paths through parent-conditioned expansion, where each child token is generated conditioned on its parent path. This construction is incompatible with diffusion language model (DLM) drafters such as DFlash, which produces all future-position distributions in a single forward pass. DDTree bridges this gap by treating high-probability tokens from each future-position distribution as candidate nodes and selecting edges between consecutive positions under a fixed node budget. However, its edge selection relies on token probability alone without modeling parent--child compatibility, so target-compatible tokens can be attached to wrong parents; moreover, its fixed budget ignores that the throughput-optimal tree size varies with the decoding state. We propose GRAFT, a draft-tree construction framework for DLM-based speculative decoding. GRAFT introduces Target-Distilled Edge Scoring (TDES), which distills parent--child preferences from target-model traces to select target-compatible edges, and State-Aware Budget Allocation (SABA), which sets the per-round tree budget by balancing expected draft gain against verification cost. Across multiple models and tasks, GRAFT achieves $2.13\times$--$6.36\times$ end-to-end speedup over autoregressive decoding while adding less than $0.5$\,ms of overhead per round, approximately $1.4\%$ of the target-model verification latency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.20375 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T10:17:37.560Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).