# LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling

arXiv: https://arxiv.org/abs/2605.00616 · HTML: https://mlsanity.com/paper/2605.00616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 12 of its 13 references that are in the map.
- First posted on arXiv 1 May 2026.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 12 of 12)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving](https://mlsanity.com/paper/2411.17651/) (2024)
- [AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving](https://mlsanity.com/paper/2601.06288/) (2026)
- [LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure](https://mlsanity.com/paper/2511.07229/) (2025)
- [Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving](https://mlsanity.com/paper/2601.00397/) (2026)
- [Frontier: Simulating the Next Generation of LLM Inference Systems](https://mlsanity.com/paper/2508.03148/) (2025)

## Abstract (arXiv)

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.