SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
read the original abstract
This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculative models to predict the LLM's outputs; the predictions are organized as a token tree, whose nodes each represent a candidate token sequence. The correctness of all candidate token sequences represented by a token tree is verified against the LLM in parallel using a novel tree-based parallel decoding mechanism. SpecInfer uses an LLM as a token tree verifier instead of an incremental decoder, which significantly reduces the end-to-end latency and computational requirement for serving generative LLMs while provably preserving model quality. Our evaluation shows that SpecInfer outperforms existing LLM serving systems by 1.5-2.8x for distributed LLM inference and by 2.6-3.5x for offloading-based LLM inference, while preserving the same generative performance. SpecInfer is publicly available at https://github.com/flexflow/FlexFlow/
This paper has not been read by Pith yet.
Forward citations
Cited by 19 Pith papers
-
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...
-
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
PSD is a training-free framework that jointly optimizes spatial unmasking and temporal speculative decoding in diffusion LLMs to reach up to 5.5x tokens per forward pass while preserving accuracy comparable to greedy ...
-
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.
-
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
o1-like models overthink easy tasks; self-training reduces compute use without accuracy loss on GSM8K, MATH500, GPQA, and AIME.
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.
-
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.
-
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
DFlare replaces DFlash's shared fused representation with per-draft-layer attention to distinct target-layer combinations, enabling deeper drafts and 2.4M training samples for 5-11% higher speedups than DFlash on Qwen...
-
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.
-
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
Domino decouples causal dependency modeling from autoregressive draft execution via a parallel backbone plus lightweight causal head and a base-anchored training curriculum, reporting up to 5.49x speedup.
-
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
PARD-2 uses Confidence-Adaptive Token optimization to align draft model training with acceptance length in speculative decoding, enabling dual-mode operation and up to 6.94x lossless speedup on Llama3.1-8B.
-
Select to Think: Unlocking SLM Potential with Local Sufficiency
Small language models can achieve near large-model reasoning performance by learning to re-rank their own top-K token predictions after distilling selection from the large model.
-
SnapKV: LLM Knows What You are Looking for Before Generation
SnapKV selects clustered important KV positions per attention head from an observation window at the prompt end, yielding 3.6x faster generation and 8.2x better memory efficiency on 16K-token inputs with comparable pe...
-
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
EAGLE resolves feature-level uncertainty in speculative sampling via one-step token advancement, delivering 2.7x-3.5x speedup on LLaMA2-Chat 70B and doubled throughput across multiple model families and tasks.
-
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.
-
Select to Think: Unlocking SLM Potential with Local Sufficiency
Select to Think reframes LLM help as ranking among SLM top-K candidates and distills the ranking ability back into the SLM for improved single-pass reasoning.
-
ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving
ConfigSpec shows that optimal configurations for speculative LLM inference conflict across goodput (favoring smallest drafters at device-specific K=2-10), cost (favoring largest drafters at K=2), and energy (favoring ...
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.