# MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

arXiv: https://arxiv.org/abs/2408.11049 · HTML: https://mlsanity.com/paper/2408.11049/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding](https://mlsanity.com/paper/2404.11912/) (2024)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [PQCache: Product Quantization-based KVCache for Long Context LLM Inference](https://mlsanity.com/paper/2407.12820/) (2024)
- [Loki: Low-rank Keys for Efficient Sparse Attention](https://mlsanity.com/paper/2406.02542/) (2024)
- [FlashDecoding++: Faster Large Language Model Inference on GPUs](https://mlsanity.com/paper/2311.01282/) (2023)
- [Memory-efficient Transformers via Top-k Attention](https://mlsanity.com/paper/2106.06899/) (2021)
- [SpreadsheetCoder: Formula Prediction from Semi-structured Context](https://mlsanity.com/paper/2106.15339/) (2021)
- [TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput](https://mlsanity.com/paper/2406.14066/) (2024)
- [The Synergy of Speculative Decoding and Batching in Serving Large Language Models](https://mlsanity.com/paper/2310.18813/) (2023)

## Built on by (most cited first, 30 of 91)

- [DFlash: Block Diffusion for Flash Speculative Decoding](https://mlsanity.com/paper/2602.06036/) (2026)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [LongCat-Flash Technical Report](https://mlsanity.com/paper/2509.01322/) (2025)
- [Energy Considerations of Large Language Model Inference and Efficiency Optimizations](https://mlsanity.com/paper/2504.17674/) (2025)
- [CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing](https://mlsanity.com/paper/2502.01976/) (2025)
- [Cognitive Memory in Large Language Models](https://mlsanity.com/paper/2504.02441/) (2025)
- [QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache](https://mlsanity.com/paper/2502.10424/) (2025)
- [Speculative Decoding and Beyond: An In-Depth Survey of Techniques](https://mlsanity.com/paper/2502.19732/) (2025)
- [ParallelSpec: Parallel Drafter for Efficient Speculative Decoding](https://mlsanity.com/paper/2410.05589/) (2024)
- [LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification](https://mlsanity.com/paper/2502.17421/) (2025)
- [Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies](https://mlsanity.com/paper/2502.05202/) (2025)
- [SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning](https://mlsanity.com/paper/2508.16201/) (2025)
- [MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE](https://mlsanity.com/paper/2505.19645/) (2025)
- [RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding](https://mlsanity.com/paper/2502.20330/) (2025)
- [Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference](https://mlsanity.com/paper/2412.18934/) (2024)
- [Kinetics: Rethinking Test-Time Scaling Laws](https://mlsanity.com/paper/2506.05333/) (2025)
- [ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios](https://mlsanity.com/paper/2604.09603/) (2026)
- [Speculative Decoding Reimagined for Multimodal Large Language Models](https://mlsanity.com/paper/2505.14260/) (2025)
- [Rectified Sparse Attention](https://mlsanity.com/paper/2506.04108/) (2025)
- [Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?](https://mlsanity.com/paper/2506.17121/) (2025)
- [Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding](https://mlsanity.com/paper/2512.01278/) (2025)
- [SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding](https://mlsanity.com/paper/2604.09557/) (2026)
- [ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts](https://mlsanity.com/paper/2503.13565/) (2025)
- [Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation](https://mlsanity.com/paper/2410.10141/) (2024)
- [Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding](https://mlsanity.com/paper/2411.13157/) (2024)
- [R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning](https://mlsanity.com/paper/2507.17307/) (2025)
- [Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions](https://mlsanity.com/paper/2508.08192/) (2025)
- [SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification](https://mlsanity.com/paper/2512.02337/) (2025)
- [Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention](https://mlsanity.com/paper/2602.07223/) (2026)
- [Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving](https://mlsanity.com/paper/2512.22420/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have become more prevalent in long-context applications such as interactive chatbots, document analysis, and agent workflows, but it is challenging to serve long-context requests with low latency and high throughput. Speculative decoding (SD) is a widely used technique to reduce latency losslessly, but the conventional wisdom suggests that its efficacy is limited to small batch sizes. In MagicDec, we show that surprisingly SD can achieve speedup even for a high throughput inference regime for moderate to long sequences. More interestingly, an intelligent drafting strategy can achieve better speedup with increasing batch size based on our rigorous analysis. MagicDec first identifies the bottleneck shifts with increasing batch size and sequence length, and uses these insights to deploy SD more effectively for high throughput inference. We leverage draft model with sparse KV cache to address the KV bottleneck, which scales with both sequence length and batch size. Additionally, we propose a theoretical model to select the optimal drafting strategy for maximum speedup. Our work highlights the broad applicability of speculative decoding in long-context serving, as it can enhance throughput and reduce latency without compromising accuracy. For moderate to long sequences, we demonstrate up to 2.51x speedup for Llama3.1-8B when serving batch sizes ranging from 32 to 256 on various types of hardware and tasks.