# AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving

arXiv: https://arxiv.org/abs/2601.06288 · HTML: https://mlsanity.com/paper/2601.06288/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 9 Jan 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, 10 of 10)

- [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)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism](https://mlsanity.com/paper/2211.13878/) (2022)
- [APEX: An Extensible and Dynamism-Aware Simulator for Automated Parallel Execution in LLM Serving](https://mlsanity.com/paper/2411.17651/) (2024)

## Built on by (most cited first, 9 of 9)

- [Frontier: Towards Comprehensive and Accurate LLM Inference Simulation](https://mlsanity.com/paper/2605.21312/) (2026)
- [How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving](https://mlsanity.com/paper/2605.28302/) (2026)
- [KernelSight-LM: A Kernel-Level LLM Inference Simulator](https://mlsanity.com/paper/2606.28565/) (2026)
- [SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference](https://mlsanity.com/paper/2603.04716/) (2026)
- [The Price of Anarchy in Disaggregated Inference](https://mlsanity.com/paper/2606.17081/) (2026)
- [LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling](https://mlsanity.com/paper/2605.00616/) (2026)
- [Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack](https://mlsanity.com/paper/2605.11232/) (2026)
- [Think Before You Grid-Search: Floor-First Triage for LLM Serving](https://mlsanity.com/paper/2607.05876/) (2026)
- [Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse Attention](https://mlsanity.com/paper/2608.03555/) (2026)

## Abstract (arXiv)

Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only distributed parallelism strategies (tensor/pipeline/expert) but also intricate framework-specific runtime parameters such as those concerning the enablement of CUDA graphs, available KV-cache memory fractions, and maximum token capacity, which drastically impact performance. The diversity of modern inference frameworks (e.g., TRT-LLM, vLLM, SGLang), each employing distinct kernels and execution policies, makes manual tuning both framework-specific and computationally prohibitive. We present AIConfigurator, a unified performance-modeling system that enables rapid, framework-agnostic inference configuration search without requiring GPU-based profiling. AIConfigurator combines (1) a methodology that decomposes inference into analytically modelable primitives - GEMM, attention, communication, and memory operations while capturing framework-specific scheduling dynamics; (2) a calibrated kernel-level performance database for these primitives across a wide range of hardware platforms and popular open-weights models (GPT-OSS, Qwen, DeepSeek, LLama, Mistral); and (3) an abstraction layer that automatically resolves optimal launch parameters for the target backend, seamlessly integrating into production-grade orchestration systems. Evaluation on production LLM serving workloads demonstrates that AIConfigurator identifies superior serving configurations that improve performance by up to 40% for dense models (e.g., Qwen3-32B) and 50% for MoE architectures (e.g., DeepSeek-V3), while completing searches within 30 seconds on average. Enabling the rapid exploration of vast design spaces - from cluster topology down to engine specific flags.