# RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

arXiv: https://arxiv.org/abs/2502.20330 · HTML: https://mlsanity.com/paper/2502.20330/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 34 of its 36 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)
- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 34)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks](https://mlsanity.com/paper/2412.15204/) (2024)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [World Model on Million-Length Video And Language With Blockwise RingAttention](https://mlsanity.com/paper/2402.08268/) (2024)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding](https://mlsanity.com/paper/2404.11912/) (2024)
- [ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification](https://mlsanity.com/paper/2405.14256/) (2024)
- [MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding](https://mlsanity.com/paper/2408.11049/) (2024)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)

## Built on by (most cited first, 14 of 14)

- [ContextPilot: Fast Long-Context Inference via Context Reuse](https://mlsanity.com/paper/2511.03475/) (2025)
- [Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention](https://mlsanity.com/paper/2602.07223/) (2026)
- [Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding](https://mlsanity.com/paper/2605.20104/) (2026)
- [Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding](https://mlsanity.com/paper/2504.01281/) (2025)
- [Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution](https://mlsanity.com/paper/2510.15312/) (2025)
- [The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus](https://mlsanity.com/paper/2603.20105/) (2026)
- [PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference](https://mlsanity.com/paper/2503.23274/) (2025)
- [A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding](https://mlsanity.com/paper/2607.27735/) (2026)
- [AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs](https://mlsanity.com/paper/2608.26004/) (2026)
- [ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference](https://mlsanity.com/paper/2609.17943/) (2026)
- [ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling](https://mlsanity.com/paper/2507.08877/) (2025)
- [KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems](https://mlsanity.com/paper/2607.24260/) (2026)
- [Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache](https://mlsanity.com/paper/2608.30252/) (2026)
- [Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help?](https://mlsanity.com/paper/2610.07350/) (2026)

## Abstract (arXiv)

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference presents significant efficiency challenges. While Speculative Decoding (SD) traditionally accelerates inference using smaller draft models, its effectiveness diminishes substantially in long-context scenarios due to memory-bound KV cache operations. We introduce Retrieval-Augmented Speculative Decoding (RAPID), which leverages RAG for both accelerating and enhancing generation quality in long-context inference. RAPID introduces the RAG drafter-a draft LLM operating on shortened retrieval contexts-to speculate on the generation of long-context target LLMs. Our approach enables a new paradigm where same-scale or even larger LLMs can serve as RAG drafters while maintaining computational efficiency. To fully leverage the potentially superior capabilities from stronger RAG drafters, we develop an inference-time knowledge transfer that enriches the target distribution by RAG. Extensive experiments on the LLaMA-3.1 and Qwen2.5 backbones demonstrate that RAPID effectively integrates the strengths of both RAG and long-context LLMs, achieving significant performance improvements (e.g., from 39.33 to 42.83 on InfiniteBench for LLaMA-3.1-8B) with more than 2x speedups for long-context inference. Our analyses also reveal the robustness of RAPID across various context lengths and retrieval quality.