Metraipolis › archive › dc_ca409473ee99

Flide: Accelerating Decision Inference with Exact State Forking — arXiv:2610.42148

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.42148
License (as archived)
CC0-1.0
Archived
2026-11-02T07:12:48.496Z
SHA-256 of the archived text
0f7584753c5072b795e018aa7721c376e44fe1f05917cb608c7d0a3f58945ec2
Stable URL of this page
https://metraipolis.com/documento/dc_ca409473ee99

How to cite

Flide: Accelerating Decision Inference with Exact State Forking — arXiv:2610.42148 — arXiv (en), https://arxiv.org/abs/2610.42148 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca409473ee99 (Metraipolis archive dc_ca409473ee99, sha256 0f7584753c5072b795e018aa7721c376e44fe1f05917cb608c7d0a3f58945ec2)
BibTeX
@misc{dcca409473ee99,
  title = {Flide: Accelerating Decision Inference with Exact State Forking — arXiv:2610.42148},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42148},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca409473ee99; sha256 0f7584753c5072b795e018aa7721c376e44fe1f05917cb608c7d0a3f58945ec2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42148. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execution. However, existing generation-oriented inference engines fail to support these workloads effectively, suffering from severe prefix recomputation overheads or distorted output probabilities. To address this challenge, we propose Flide, an efficient and exact inference engine that decouples the logical tree structure of a decision request from its physical execution within a single flattened token stream. Through ForkAttention, Flide navigates request dependencies using GPU-resident indices across both standard attention and recurrent Gated DeltaNet layers, guaranteeing in exact arithmetic that every query branch evaluates identically to an isolated forward pass. By expressing branch topologies directly in GPU-resident metadata, Flide accommodates diverse request mixtures with a compact set of pre-recorded execution graphs while enabling expanding agent histories to resume from checkpoints saved in earlier passes. Extensive evaluations on public hybrid and decision models demonstrate that Flide answers queries up to 9.5 times faster than vLLM and SGLang while staying closest to a float32 reference in total variation distance. By unifying physical execution throughput with mathematical exactness, Flide establishes a principled foundation for scalable, latency-critical decision intelligence in agent systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.42148 — 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 2026-11-02T07:07:14.212Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).