REVIEW 40 cited by
Break the Sequential Dependency of LLM Inference Using Lookahead 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
Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
read the original abstract
Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelerating LLM decoding often require a draft model (e.g., speculative decoding), which is nontrivial to obtain and unable to generalize. In this paper, we introduce Lookahead decoding, an exact, parallel decoding algorithm that accelerates LLM decoding without needing auxiliary models or data stores. It allows trading per-step log(FLOPs) to reduce the number of total decoding steps, is more parallelizable on single or multiple modern accelerators, and is compatible with concurrent memory-efficient attention (e.g., FlashAttention). Our implementation of Lookahead decoding can speed up autoregressive decoding by up to 1.8x on MT-bench and 4x with strong scaling on multiple GPUs in code completion tasks. Our code is avialable at https://github.com/hao-ai-lab/LookaheadDecoding
Forward citations
Cited by 40 Pith papers
-
Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding
A post-conversion training objective that reconstructs the original attention function of MLA-converted draft models improves speculative-decoding acceptance in most of 64 matched task cells.
-
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
-
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Local Branch Routing (LBR) is a token-level framework for test-time scaling in language models that uses local branch hidden states for routing and supports end-to-end RL, showing gains in Pass@1 and Pass@32 on math r...
-
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
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.
-
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Graft combines pruning and retrieval in a sequential mechanism to build hybrid draft trees for speculative decoding, delivering up to 5.41× speedup and 21.8% better average speedup than EAGLE-3 on large models.
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-13% higher mean speedup than EAGLE-3 at 44-52% drafting cost via block-iterative drafting with hidden-state inheritance, dynamic rank-head branching, valid-prefix masking, and optional cost-aware ...
-
Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots
Reference-augmented learning with RNN surrogate and stochastic perturbations cuts average position error by 50.9% for 6-DOF tracking on a three-section TDCR compared to non-augmented baselines.
-
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Aurora unifies speculative decoder training and serving via asynchronous RL on inference traces, delivering 1.5x day-0 speedup on frontier models and 1.25x adaptation gains on distribution shifts.
-
VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
-
TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
TokenTiming uses dynamic time warping on re-encoded token sequences to enable speculative decoding between models with different vocabularies, reporting 1.57x speedup.
-
FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new ...
-
From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving
KV-cache serving systems concentrate into five archetypes under a four-axis taxonomy, with ownership explaining residual distributed design variance and seven measurement gaps blocking next steps.
-
The Context-Ready Transformer
Context-ready transformer adds a correction network to pre-contextualize tokens in a D-layer block, turning the model recurrent for inference while allowing K-step unrolled parallel training, with reported gains over ...
-
CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference
CLP is a lightweight linear predictor for safe multi-token spans in LLM decoding that delivers 1.14x-1.29x speedup on Qwen2.5 models with zero measured quality degradation.
-
Streaming Communication in Multi-Agent Reasoning
Streaming an agent's reasoning steps to the next agent as they are produced cuts latency and, when early steps are more reliable than late ones, also improves final accuracy.
-
Streaming Communication in Multi-Agent Reasoning
StreamMA introduces streaming communication in multi-agent reasoning to reduce latency via pipelining and improve effectiveness by leveraging reliable early steps, with closed-form analysis and a step-level scaling law.
-
An Interpretable Latency Model for Speculative Decoding in LLM Serving
The paper presents an interpretable latency model for speculative decoding that infers effective batch size via Little's Law and decomposes demand to predict and explain performance across serving loads, validated on ...
-
Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing
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.
-
CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
CATS achieves up to 5.08x wall-clock speedup for LLM generation on edge devices via memory-matched cascaded tree speculation, outperforming prior methods by 1.45x with no quality loss.
-
SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting
SpecBlock achieves 8-19% higher speedup than EAGLE-3 in LLM speculative decoding by using repeated block expansions with hidden-state inheritance, a dynamic rank head, and a valid-prefix training mask.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing l...
-
NVLLM: A 3D NAND-Centric Architecture Enabling Edge on-Device LLM Inference
NVLLM offloads FFN computations to integrated 3D NAND flash with page-level access and keeps attention in DRAM, delivering 16.7x-37.9x speedups over GPU out-of-core baselines for models up to 30B parameters.
-
Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots
Reference-augmented offline policy optimization through a differentiable RNN dynamics model cuts TDCR tip-position error by ~51% versus non-augmented training and outperforms Jacobian controllers across speeds.
-
SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
SpecBound achieves up to 2.33x wall-time speedup in LLM inference via adaptive bounded self-speculation and layer-wise confidence calibration while preserving exact output equivalence.
-
Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism
Double achieves up to 5.3x inference speedup on 70B LLMs via synchronous double retrieval speculative parallelism that is lossless and outperforms trained baselines like EAGLE-3.
-
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
Seer improves synchronous LLM RL rollout throughput by up to 2.04x and reduces long-tail latency by 72-94% via divided rollout, context-aware scheduling, and adaptive grouped speculative decoding based on prompt simil...
-
HiSpec: Hierarchical Speculative Decoding for LLMs
HiSpec uses early-exit layers to verify draft tokens midway through the model, reporting 1.28×-2.01× faster decoding over baseline speculative decoding, but the accuracy claim is not empirically tested.
-
Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs
Spiffy speeds up diffusion LLM inference up to about 3x (and up to 7.9x with parallel decoding) by verifying multiple candidate unmasked states in one batched model call, while preserving greedy output.
-
KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems
KAP compiles structured knowledge priors into runtime access plans that cut proposal-time KV access to 5.5% at 128K while matching full-context QA quality and yielding up to 1.19× decode throughput.
-
WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning
A workload-aware rollout system combining suffix-based speculative decoding (low load) and cache-aware scheduling (high load) speeds synchronous agentic RL rollout by 1.4-1.6x.
-
Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion
No detectable safety divergence between target-only and speculative decoding at temperature zero under TAIS criteria on 48,072 samples across safety benchmarks.
-
Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding
Cassandra is a self-speculative decoding system that builds a draft model via fine-grained data selection and optimized pruning/mantissa truncation, achieving up to 2.41x speedup over BF16 and 1.81x more tokens than E...
-
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
CSD recovers valid but lexically divergent tokens in speculative decoding via frequency-guided candidates from historical rejections and probability-ratio gating, delivering up to 2.33x speedup while preserving accuracy.
-
Multi-Drafter Speculative Decoding with Alignment Feedback
MetaSD integrates multiple heterogeneous drafters into speculative decoding, dynamically selecting them via alignment feedback modeled as a multi-armed bandit to consistently outperform single-drafter baselines.
-
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
ECHO uses sparse gating and elastic budget pivoting in a super-tree structure to achieve up to 5.35x speedup for LLM inference under high concurrency.
-
Parallel Decoder Transformer: Planner-Conditioned Latent Coordination for Model-Intrinsic Parallel Generation
A Parallel Decoder Transformer architecture for multi-lane parallel text generation is proposed, but the paper's own evidence is incomplete and internally contradictory.
-
Reference-Augmented Learning for Precise Tracking Policy of Tendon-Driven Continuum Robots
A reference-augmented offline learning framework for 6-DOF tracking control of tendon-driven continuum robots achieves 50.9% lower average position error than non-augmented baselines.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A comprehensive reference book organizing existing techniques for agentic AI systems across LLM substrate, reasoning, agent design patterns, inter-agent coordination, and production deployment.
-
Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)
A literature survey of Small Language Models (1-8B parameters) that can perform comparably or better than larger models, covering general-purpose and task-specific approaches plus creation techniques.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.