# Speculative Prefill: Turbocharging TTFT with Lightweight and Training-Free Token Importance Estimation

arXiv: https://arxiv.org/abs/2502.02789 · HTML: https://mlsanity.com/paper/2502.02789/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 5 Feb 2025.

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

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [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)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention](https://mlsanity.com/paper/2407.02490/) (2024)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference](https://mlsanity.com/paper/2406.18139/) (2024)
- [SCBench: A KV Cache-Centric Analysis of Long-Context Methods](https://mlsanity.com/paper/2412.10319/) (2024)
- [SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention](https://mlsanity.com/paper/2406.15486/) (2024)

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

- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [REFRAG: Rethinking RAG based Decoding](https://mlsanity.com/paper/2509.01092/) (2025)
- [Draft-based Approximate Inference for LLMs](https://mlsanity.com/paper/2506.08373/) (2025)
- [HAMburger: Accelerating LLM Inference via Token Smashing](https://mlsanity.com/paper/2505.20438/) (2025)
- [SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling](https://mlsanity.com/paper/2505.24179/) (2025)
- [When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges](https://mlsanity.com/paper/2601.08343/) (2026)
- [Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models](https://mlsanity.com/paper/2603.02631/) (2026)
- [Don't Pay Attention](https://mlsanity.com/paper/2506.11305/) (2025)
- [CLAA: Cross-Layer Attention Aggregation for Accelerating LLM Prefill](https://mlsanity.com/paper/2602.16054/) (2026)
- [LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning](https://mlsanity.com/paper/2606.01336/) (2026)
- [Multi-Modal Agents for Power Distribution Defect Detection: An Evaluation of Foundation Models](https://mlsanity.com/paper/2606.12969/) (2026)
- [Audio Token Attention Is Predictable Before the Language Model Runs](https://mlsanity.com/paper/2609.38878/) (2026)
- [Lend Me Your Eyes: Instruction-Aware Text Embeddings via Attention Relay](https://mlsanity.com/paper/2610.05564/) (2026)
- [PAIR: Memory-Efficient and Fast Inference with Reading--Reasoning Fusion](https://mlsanity.com/paper/2610.16003/) (2026)

## Abstract (arXiv)

Improving time-to-first-token (TTFT) is an essentially important objective in modern large language model (LLM) inference engines. Optimizing TTFT directly results in higher maximal QPS and meets the requirements of many critical applications. However, boosting TTFT is notoriously challenging since it is compute-bounded and the performance bottleneck shifts from the self-attention that many prior works focus on to the MLP part. In this work, we present SpecPrefill, a training free framework that accelerates the inference TTFT for both long and medium context queries based on the following insight: LLMs are generalized enough to preserve the quality given only a carefully chosen subset of prompt tokens. At its core, SpecPrefill leverages a lightweight model to speculate locally important tokens based on the context. These tokens, along with the necessary positional information, are then sent to the main model for processing. We evaluate SpecPrefill with a diverse set of tasks, followed by a comprehensive benchmarking of performance improvement both in a real end-to-end setting and ablation studies. SpecPrefill manages to serve Llama-3.1-405B-Instruct-FP8 with up to 7× maximal end-to-end QPS on real downstream tasks and 7.66× TTFT improvement.