Metraipolis › archive › dc_e234fef11f43
Weights That Stay: On-Chip Megakernels for Serial Heads in Speculative Decoding — arXiv:2611.00506
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00506
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:12:34.349Z
- SHA-256 of the archived text
d87b253da31f3f0f00f562c8b547e2c34ebc1a33b84867f462043e8d9816877b- Stable URL of this page
https://metraipolis.com/documento/dc_e234fef11f43
How to cite
Weights That Stay: On-Chip Megakernels for Serial Heads in Speculative Decoding — arXiv:2611.00506 — arXiv (en), https://arxiv.org/abs/2611.00506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e234fef11f43 (Metraipolis archive dc_e234fef11f43, sha256 d87b253da31f3f0f00f562c8b547e2c34ebc1a33b84867f462043e8d9816877b)
BibTeX
@misc{dce234fef11f43,
title = {Weights That Stay: On-Chip Megakernels for Serial Heads in Speculative Decoding — arXiv:2611.00506},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00506},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e234fef11f43; sha256 d87b253da31f3f0f00f562c8b547e2c34ebc1a33b84867f462043e8d9816877b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Parallel speculative drafters use a lightweight serial head to recover token dependencies within a block generated in parallel. Each head step updates only a small state, yet projects that state through the same vocabulary-sized matrix. Step-wise execution repeatedly transfers this large, immutable projection, making the head a meaningful source of latency despite its low arithmetic cost. We present Weights That Stay, an execution design that keeps projection shards on chip for the entire serial draft walk. A persistent megakernel couples weight residency with GPU-side token selection and state advancement, reusing resident weights while exchanging only compact state between steps. The design supports full or partial residency and accommodates both Markov and recurrent heads on H100 and B200. Integrated into SGLang, Weights That Stay improves throughput for Markov drafting on Qwen3-4B and Qwen3-8B, with gains of up to 12.3%. At the head level, the DSpark walk is up to 11.6$\times$ faster than the fastest measured SGLang reference path. These results show that aligning weight residency with the full draft walk translates cross-step reuse into end-to-end serving gains. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.00506 — 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 2026-11-03T11:00:07.140Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).