Metraipolis › archive › dc_2628e7d72ca4

Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models — arXiv:2610.19855

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19855
License (as archived)
CC0-1.0
Archived
2026-10-15T14:17:51.750Z
SHA-256 of the archived text
c69678c1f8f62d87beecefa4142a3a796c3f4741dc152d32c56b17848fb5a4ba
Stable URL of this page
https://metraipolis.com/documento/dc_2628e7d72ca4

How to cite

Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models — arXiv:2610.19855 — arXiv (en), https://arxiv.org/abs/2610.19855 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2628e7d72ca4 (Metraipolis archive dc_2628e7d72ca4, sha256 c69678c1f8f62d87beecefa4142a3a796c3f4741dc152d32c56b17848fb5a4ba)
BibTeX
@misc{dc2628e7d72ca4,
  title = {Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models — arXiv:2610.19855},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19855},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2628e7d72ca4; sha256 c69678c1f8f62d87beecefa4142a3a796c3f4741dc152d32c56b17848fb5a4ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19855. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) models are the industry standard, Diffusion Language Models (DLLMs) have emerged as a promising alternative capable of parallel token generation. In this paper, we perform a comparative energy benchmark of diffusion models (LLaDA-8B, Dream-7B) against AR counterparts (Llama-3.1-8B, Qwen-2.5-7B). We analyze the trade-offs between model architecture, KV-cache optimization, and Joules-per-token efficiency. Our results show that at longer sequences (200--600 tokens), diffusion models achieve 2.5--2.7 J/token, approximately 2$\times$ more efficient than AR models with KV-cache (5.3--5.7 J/token). KV-cache provides substantial benefits for AR models at longer sequences (50--70\% energy reduction).

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19855 — 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 2026-10-15T13:53:35.660Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).