SlimSpec replaces the standard LM-head in draft models with a low-rank version to deliver 4-5x faster speculative decoding while preserving full vocabulary and competitive acceptance rates.
hub
Eagle-2: Faster inference of language models with dynamic draft trees
22 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
22
Pith papers citing it
1
external citations · Pith
abstract
Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly assuming that the acceptance rate of draft tokens depends only on their position. Interestingly, we found that the acceptance rate of draft tokens is also context-dependent. In this paper, building upon EAGLE, we propose EAGLE-2, which introduces a new technique of context-aware dynamic draft tree into drafting modeling. This improvement leverages the fact that the draft model of EAGLE is well-calibrated: the confidence scores from the draft model approximate acceptance rates with small errors. We conducted extensive evaluations on three series of LLMs and six tasks, with EAGLE-2 achieving speedup ratios 3.05x-4.26x, which is 20%-40% faster than EAGLE-1. EAGLE-2 also ensures that the distribution of the generated text remains unchanged, making it a lossless acceleration algorithm.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
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.
TokenTiming uses dynamic time warping on re-encoded token sequences to enable speculative decoding between models with different vocabularies, reporting 1.57x speedup.
Per-position AR prediction entropy jointly drives speculative AR decoding and an anti-symmetric single-step drift decoder, yielding 3.8–5.5× faster hybrid visual generation without distillation.
JetSpec trains a causal draft head to produce branch-consistent trees aligned with target autoregressive scores, achieving up to 9.64x speedup on MATH-500 and outperforming prior SD baselines on Qwen3 models.
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.
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.
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.
VeriCache turns lossy KV cache compression into lossless LLM inference by drafting with compressed cache and verifying drafts with full cache, achieving up to 4x throughput with identical outputs.
CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to-image models without quality loss.
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
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 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 similarity observations.
Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.
BlockPilot is an instance-adaptive policy that predicts optimal block size from the prefilling representation for diffusion speculative decoding, reporting 5.92 acceptance length and 4.20x speedup on Qwen3-4B.
EntMTP is a training-free entropy-guided scheduler for multi-token prediction that dynamically selects from task-specific Pareto-optimal trees to accelerate LLM inference by up to 1.36x on benchmarks without quality loss.
Heima compresses verbose CoT into hidden thinking tokens via information-theoretic analysis and an adaptive interpreter, claiming maintained or improved zero-shot accuracy on reasoning benchmarks.
citing papers explorer
-
SlimSpec: Low-Rank Draft LM-Head for Accelerated Speculative Decoding
SlimSpec replaces the standard LM-head in draft models with a low-rank version to deliver 4-5x faster speculative decoding while preserving full vocabulary and competitive acceptance rates.
-
NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
-
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.
-
KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
-
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.
-
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.
-
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Per-position AR prediction entropy jointly drives speculative AR decoding and an anti-symmetric single-step drift decoder, yielding 3.8–5.5× faster hybrid visual generation without distillation.
-
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
JetSpec trains a causal draft head to produce branch-consistent trees aligned with target autoregressive scores, achieving up to 9.64x speedup on MATH-500 and outperforming prior SD baselines on Qwen3 models.
-
From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
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.
-
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.
-
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation
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.
-
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
VeriCache turns lossy KV cache compression into lossless LLM inference by drafting with compressed cache and verifying drafts with full cache, achieving up to 4x throughput with identical outputs.
-
CASCADE: Context-Aware Relaxation for Speculative Image Decoding
CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to-image models without quality loss.
-
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
-
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 similarity observations.
-
Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
Speculative Verification adds a companion model that estimates draft-target alignment via information gain to dynamically set verification length, delivering up to 2x speedup over standard speculative decoding across tested models and batch sizes.
-
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
BlockPilot is an instance-adaptive policy that predicts optimal block size from the prefilling representation for diffusion speculative decoding, reporting 5.92 acceptance length and 4.20x speedup on Qwen3-4B.
-
EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction
EntMTP is a training-free entropy-guided scheduler for multi-token prediction that dynamically selects from task-specific Pareto-optimal trees to accelerate LLM inference by up to 1.36x on benchmarks without quality loss.
-
Efficient Reasoning with Hidden Thinking
Heima compresses verbose CoT into hidden thinking tokens via information-theoretic analysis and an adaptive interpreter, claiming maintained or improved zero-shot accuracy on reasoning benchmarks.
- DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding
- An Empirical Study of Speculative Decoding on Software Engineering Tasks