# ReaLM: Reliable and Efficient Large Language Model Inference with Statistical Algorithm-Based Fault Tolerance

arXiv: https://arxiv.org/abs/2503.24053 · HTML: https://mlsanity.com/paper/2503.24053/

## Key facts

- Cited by 5 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 17 of its 55 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## 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, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [RPTQ: Reorder-based Post-training Quantization for Large Language Models](https://mlsanity.com/paper/2304.01089/) (2023)
- [NVIDIA Tensor Core Programmability, Performance & Precision](https://mlsanity.com/paper/1803.04014/) (2018)
- [Silent Data Corruptions at Scale](https://mlsanity.com/paper/2102.11245/) (2021)
- [ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators](https://mlsanity.com/paper/1802.03806/) (2018)
- [On the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation](https://mlsanity.com/paper/1806.09679/) (2018)
- [Analyzing and Improving Fault Tolerance of Learning-Based Navigation Systems](https://mlsanity.com/paper/2111.04957/) (2021)

## Built on by (most cited first, 5 of 5)

- [KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing](https://mlsanity.com/paper/2512.03608/) (2025)
- [FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors](https://mlsanity.com/paper/2605.08594/) (2026)
- [Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study](https://mlsanity.com/paper/2601.19912/) (2025)
- [Machines that know they are aging: a framework for hardware-aware autonomous intelligence](https://mlsanity.com/paper/2607.28451/) (2026)
- [Syndrome Decoding for Silent Data Corruption in Quantized Integer GPU Arithmetic](https://mlsanity.com/paper/2609.19743/) (2026)

## Abstract (arXiv)

The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often reserve a large voltage margin or leverage algorithm-based fault tolerance (ABFT) techniques to ensure LLM inference correctness. However, previous methods often overlook the inherent fault tolerance of LLMs, leading to high computation and energy overhead. To enable reliable yet efficient LLM inference, in this paper, we propose a novel algorithm/circuit co-design framework, dubbed ReaLM. For the first time, we systematically characterize the fault tolerance of LLMs by performing a large-scale error injection study of representative LLMs and natural language understanding tasks. Then, we propose a statistical ABFT algorithm that fully leverages the error robustness to minimize error recovery as much as possible. We also customize the error detection circuits to enable a low-cost online collection of error statistics. Extensive experiments show that with only 1.42% circuit area and 1.79% power overhead, our ReaLM can reduce perplexity degradation from 18.54 to 0.29. Compared to existing methods, ReaLM consistently reduces recovery costs across different operating voltages and improves energy efficiency by up to 35.83% without compromising LLM performance. Our error injection code is available at https://github.com/PKU-SEC-Lab/ReaLM_DAC25/