Pith. sign in

REVIEW 4 cited by

DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.12000 v2 pith:J6E5AMRI submitted 2025-07-16 eess.SP

DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding

classification eess.SP
keywords decodingdssdinferencelanguagespeculativesplittransmissioncollaborative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) have transformed natural language processing but face critical deployment challenges in device-edge systems due to resource limitations and communication overhead. To address these issues, collaborative frameworks have emerged that combine small language models (SLMs) on devices with LLMs at the edge, using speculative decoding (SD) to improve efficiency. However, existing solutions often trade inference accuracy for latency or suffer from high uplink transmission costs when verifying candidate tokens. In this paper, we propose Distributed Split Speculative Decoding (DSSD), a novel architecture that not only preserves the SLM-LLM split but also partitions the verification phase between the device and edge. In this way, DSSD replaces the uplink transmission of multiple vocabulary distributions with a single downlink transmission, significantly reducing communication latency while maintaining inference quality. Experiments show that our solution outperforms current methods, and codes are at: https://github.com/JasonNing96/DSSD-Efficient-Edge-Computing

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference

    cs.IT 2026-04 unverdicted novelty 7.0

    WISV uses a channel-aware semantic acceptance policy on hidden representations to boost accepted sequence length by up to 60.8% and cut interaction rounds by 37.3% in distributed speculative decoding, with under 1% ac...

  2. CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative Decoding

    cs.AI 2026-05 unverdicted novelty 6.0

    CoVSpec achieves up to 2.21x higher throughput and over 96% lower communication overhead for device-edge VLM inference via training-free visual token reduction, adaptive drafting, and decoupled parallel verification-c...

  3. WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

    cs.DC 2026-01 unverdicted novelty 6.0

    WISP suppresses wasted drafting time and verification interference in edge-cloud speculative LLM serving through dynamic drafting and SLO-aware batching, delivering up to 2.1x capacity and 1.94x goodput gains over cen...

  4. Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

    cs.CR 2026-07 conditional novelty 5.0

    An edge-cloud LLM serving scheme splits the final projection along the hidden dimension, keeps cache control and LoRA modules on-device, and reports 29-46% lower per-token latency and 56-67% lower downlink payloads th...