Pith. sign in

REVIEW 11 cited by

Sequoia: Scalable, Robust, and Hardware-aware 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 2402.12374 v3 pith:BWQXTQUK submitted 2024-02-19 cs.CL

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

classification cs.CL
keywords sequoiatimesdecodingspeculativehardware-awareinferenceintroducesrobust
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

As the usage of large language models (LLMs) grows, performing efficient inference with these models becomes increasingly important. While speculative decoding has recently emerged as a promising direction for speeding up inference, existing methods are limited in their ability to scale to larger speculation budgets, and adapt to different hyperparameters and hardware. This paper introduces Sequoia, a scalable, robust, and hardware-aware algorithm for speculative decoding. To attain better scalability, Sequoia introduces a dynamic programming algorithm to find the optimal tree structure for the speculated tokens. To achieve robust speculative performance, Sequoia uses a novel sampling and verification method that outperforms prior work across different decoding temperatures. Finally, Sequoia introduces a hardware-aware tree optimizer that maximizes speculative performance by automatically selecting the token tree size and depth for a given hardware platform. Evaluation shows that Sequoia improves the decoding speed of Llama2-7B, Llama2-13B, and Vicuna-33B on an A100 by up to $4.04\times$, $3.73\times$, and $2.27\times$. For offloading setting on L40, Sequoia achieves as low as 0.56 s/token for exact Llama2-70B inference latency, which is $9.96\times$ on our optimized offloading system (5.6 s/token), $9.7\times$ than DeepSpeed-Zero-Inference, $19.5\times$ than Huggingface Accelerate.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Trees from Marginals: Autoregressive drafting with factorized priors

    cs.LG 2026-07 accept novelty 7.0

    Weaver restores conditional dependencies on top-K factorized marginals to build high-acceptance draft trees, plus a fused GDN tree-verify kernel, yielding 4.37× AR speedup and 24.7% over DFlash.

  2. D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models

    cs.DC 2026-06 unverdicted novelty 7.0

    D^2SD uses two diffusion drafters in a prefix tree structure with confidence scores to select and recover alternative draft sequences, achieving higher acceptance rates in speculative decoding.

  3. Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

    cs.LG 2026-05 unverdicted novelty 7.0

    BASTION is a budget-aware speculative decoding framework with adaptive tree-structured block diffusion drafting that reports up to 6.61x speedup and 39% improvement over block-diffusion baselines.

  4. CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference

    cs.IT 2026-05 unverdicted novelty 7.0

    CR^2 matches full-information routing performance for device-edge LLM inference using only device-side signals and cuts normalized deployment cost by up to 16.9% at matched accuracy.

  5. Dustin: Draft-Augmented Sparse Verification for Efficient Long-Context Generation with Speculative Decoding

    cs.CL 2026-06 unverdicted novelty 6.0

    Dustin reports 27.85x self-attention and 9.17x end-to-end speedups at 32k length on Qwen2.5-72B using draft-augmented sparse verification with negligible accuracy loss on PG-19 and LongBench.

  6. From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

    cs.CV 2026-06 unverdicted novelty 6.0

    A 1D token interface with Selective Token Editing improves multimodal image fusion by modeling global appearance factors separately from local 2D structures, yielding best overall performance on four benchmarks.

  7. DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

    cs.LG 2026-05 unverdicted novelty 6.0

    DREAM-S combines neural architecture search, target-aware supernet training, and attention-entropy-guided distillation to accelerate speculative decoding in VLMs, reporting up to 3.85x speedup over standard methods.

  8. Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing

    cs.CL 2026-05 unverdicted novelty 6.0

    PPOW uses window-level RL with cost-aware speedup and proximity rewards plus adaptive divergence-aware windowing to reach 6.29-6.52 acceptance lengths and 3.39-4.36x speedups in speculative decoding.

  9. When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

    cs.CL 2026-04 unverdicted novelty 6.0

    KV cache reuse improves long-range draft acceptance rates in speculative decoding but delivers only marginal end-to-end speedups because shallow drafters cannot accurately estimate target queries and receive sparse gr...

  10. When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

    cs.CL 2026-04 unverdicted novelty 6.0

    KV cache reuse improves long-range draft acceptance in speculative decoding but delivers only marginal end-to-end speedups due to drafter limitations.

  11. Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion

    cs.LG 2026-06 unverdicted novelty 5.0

    No detectable safety divergence between target-only and speculative decoding at temperature zero under TAIS criteria on 48,072 samples across safety benchmarks.