# TIDE: Temporal Incremental Draft Engine for Self-Improving LLM Inference

arXiv: https://arxiv.org/abs/2602.05145 · HTML: https://mlsanity.com/paper/2602.05145/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Self-rewarding alignment and self-training, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 36 of its 53 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)
- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 36)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [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)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding](https://mlsanity.com/paper/2402.05109/) (2024)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths](https://mlsanity.com/paper/2405.19715/) (2024)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving](https://mlsanity.com/paper/2404.02015/) (2024)
- [Recurrent Drafter for Fast Speculative Decoding in Large Language Models](https://mlsanity.com/paper/2403.09919/) (2024)
- [TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput](https://mlsanity.com/paper/2406.14066/) (2024)
- [Decoding Speculative Decoding](https://mlsanity.com/paper/2402.01528/) (2024)
- [M'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity](https://mlsanity.com/paper/2404.14527/) (2024)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability](https://mlsanity.com/paper/2410.18351/) (2024)
- [HexGen-2: Disaggregated Generative Inference of LLMs in Heterogeneous Environment](https://mlsanity.com/paper/2502.07903/) (2025)
- [BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms](https://mlsanity.com/paper/2505.15141/) (2025)

## Built on by (most cited first, 1 of 1)

- [SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting](https://mlsanity.com/paper/2605.07243/) (2026)

## Abstract (arXiv)

Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads. We present TIDE (Temporal Incremental Draft Engine), a serving-engine-native framework that integrates online draft adaptation directly into high-performance LLM inference systems. TIDE reuses target model's intermediate hidden states generated during inference as training signals for draft adaptation, thereby avoiding additional target model computation and serving-time overhead. It employs adaptive runtime control to activate speculation and draft model training only when beneficial. TIDE exploits heterogeneous clusters by mapping inference and training to appropriate GPU classes. Across diverse real-world workloads, TIDE achieves up to 1.66× throughput over no-speculation baselines while recovering performance on misaligned workloads where static draft models degrade throughput. TIDE also reduces training time by up to 3.02× and storage requirements by 24× compared to existing draft training approaches, and improves system throughput by up to 1.22× on heterogeneous GPU clusters.