# TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput

arXiv: https://arxiv.org/abs/2406.14066 · HTML: https://mlsanity.com/paper/2406.14066/

## Key facts

- Cited by 37 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 18 of its 38 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (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)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [Hydragen: High-Throughput LLM Inference with Shared Prefixes](https://mlsanity.com/paper/2402.05099/) (2024)
- [The Synergy of Speculative Decoding and Batching in Serving Large Language Models](https://mlsanity.com/paper/2310.18813/) (2023)
- [BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models](https://mlsanity.com/paper/2401.12522/) (2024)

## Built on by (most cited first, 30 of 37)

- [MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding](https://mlsanity.com/paper/2408.11049/) (2024)
- [SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications](https://mlsanity.com/paper/2411.04975/) (2024)
- [Dynamic Depth Decoding: Faster Speculative Decoding for LLMs](https://mlsanity.com/paper/2409.00142/) (2024)
- [TETRIS: Optimal Draft Token Selection for Batch Speculative Decoding](https://mlsanity.com/paper/2502.15197/) (2025)
- [Scaling Speculative Decoding with Lookahead Reasoning](https://mlsanity.com/paper/2506.19830/) (2025)
- [Utility-Driven Speculative Decoding for Mixture-of-Experts](https://mlsanity.com/paper/2506.20675/) (2025)
- [ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios](https://mlsanity.com/paper/2604.09603/) (2026)
- [ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts](https://mlsanity.com/paper/2503.13565/) (2025)
- [SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models](https://mlsanity.com/paper/2503.15921/) (2025)
- [SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding](https://mlsanity.com/paper/2506.11309/) (2025)
- [What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding](https://mlsanity.com/paper/2506.06998/) (2025)
- [Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design](https://mlsanity.com/paper/2511.20048/) (2025)
- [Closer Look at Efficient Inference Methods: A Survey of Speculative Decoding](https://mlsanity.com/paper/2411.13157/) (2024)
- [Collaborative Speculative Inference for Efficient LLM Inference Serving](https://mlsanity.com/paper/2503.10325/) (2025)
- [Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models](https://mlsanity.com/paper/2606.08446/) (2026)
- [TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation](https://mlsanity.com/paper/2502.18890/) (2025)
- [Fast LLM Post-training via Decoupled and Fastest-of-N Speculation](https://mlsanity.com/paper/2511.16193/) (2025)
- [Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs](https://mlsanity.com/paper/2512.20573/) (2025)
- [Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem](https://mlsanity.com/paper/2510.22876/) (2025)
- [SSSD: Simply-Scalable Speculative Decoding](https://mlsanity.com/paper/2411.05894/) (2024)
- [HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding](https://mlsanity.com/paper/2505.13254/) (2025)
- [Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels](https://mlsanity.com/paper/2412.18106/) (2024)
- [TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference](https://mlsanity.com/paper/2602.05145/) (2026)
- [MineDraft: A Framework for Batch Parallel Speculative Decoding](https://mlsanity.com/paper/2603.18016/) (2026)
- [Optimus: Elastic Decoding for Efficient Diffusion LLM Serving](https://mlsanity.com/paper/2605.24832/) (2026)
- [Enabling KV Caching of Shared Prefix for Diffusion Language Models](https://mlsanity.com/paper/2606.07571/) (2026)
- [Speculation at a Distance: Where Edge-Cloud Speculative Decoding Actually Pays Off](https://mlsanity.com/paper/2606.25091/) (2026)
- [TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding](https://mlsanity.com/paper/2609.22098/) (2026)
- [OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs](https://mlsanity.com/paper/2510.07535/) (2025)
- [Regulating Branch Parallelism in LLM Serving](https://mlsanity.com/paper/2605.06914/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) serving systems batch concurrent user requests to achieve efficient serving. However, in real-world deployments, such inter-request parallelism from batching is often limited by external factors such as low request rates or memory constraints. Recent works focus on intra-request parallelism from speculative decoding as a solution to this problem. Unfortunately, benefits from intra-request parallelism are often fragile, as speculative decoding causes overhead, and speculated tokens may miss. We observe that speculative decoding may degrade LLM serving performance if added naively without tuning to the incoming requests and the speculation method. To alleviate the need for expert tuning and make speculative decoding more robust, we present TurboSpec, a speculation control system that automatically profiles the execution environment and utilizes a feedback-based algorithm to dynamically adjust the amount of intra-request parallelism in LLM serving. TurboSpec predicts "goodput" - the amount of successfully generated tokens - to evaluate and adjust intra-request parallelism amount to that with the highest goodput in runtime. We implement TurboSpec on a real-world LLM serving system vLLM and demonstrate its effectiveness across diverse workloads and hardware configurations, providing consistent performance improvements across all test scenarios.