# SAIL: SRAM-Accelerated LLM Inference System with Lookup-Table-based GEMV

arXiv: https://arxiv.org/abs/2509.25853 · HTML: https://mlsanity.com/paper/2509.25853/

## Key facts

- Cited by 1 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 38 of its 71 references that are in the map.
- First posted on arXiv 30 Sep 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, 30 of 38)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [AI and Memory Wall](https://mlsanity.com/paper/2403.14123/) (2024)
- [Full Stack Optimization of Transformer Inference: a Survey](https://mlsanity.com/paper/2302.14017/) (2023)
- [Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models](https://mlsanity.com/paper/2402.07033/) (2024)
- [The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research](https://mlsanity.com/paper/2010.15581/) (2020)
- [QAQ: Quality Adaptive Quantization for LLM KV Cache](https://mlsanity.com/paper/2403.04643/) (2024)
- [T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge](https://mlsanity.com/paper/2407.00088/) (2024)
- [D'ej`aVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving](https://mlsanity.com/paper/2403.01876/) (2024)
- [SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models](https://mlsanity.com/paper/2405.06219/) (2024)
- [Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks](https://mlsanity.com/paper/1805.03718/) (2018)
- [Democratising AI: Multiple Meanings, Goals, and Methods](https://mlsanity.com/paper/2303.12642/) (2023)
- [Efficient LLM Inference on CPUs](https://mlsanity.com/paper/2311.00502/) (2023)
- [What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation](https://mlsanity.com/paper/2403.06408/) (2024)
- [Large Language Model Supply Chain: A Research Agenda](https://mlsanity.com/paper/2404.12736/) (2024)
- [Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels](https://mlsanity.com/paper/2406.17415/) (2024)
- [Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware](https://mlsanity.com/paper/2110.01709/) (2021)
- [NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention](https://mlsanity.com/paper/2403.01273/) (2024)

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

- [PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2605.23027/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However, efficient LLM inference on CPUs faces two fundamental challenges: (1) existing CPU architectures struggle with low-precision arithmetic required by quantized models, where optimal bit precision varies across models and layers; and (2) the memory-bound nature of the token generation phase creates severe performance bottlenecks. To address these challenges, we propose SAIL (SRAM-Accelerated Inference of LLMs), a CPU-based inference solution that efficiently supports arbitrary bit precisions with minimal overhead. SAIL integrates three key innovations: First, we introduce Batched LUT-based General Matrix-Vector Multiplication (LUT-GEMV) with SRAM-based processing-in-memory, enabling high data reuse through lookup tables and reducing memory movement. Second, our Pattern-Aware LUT optimization identifies and exploits redundancy in input activation patterns, reducing computation cycles by 13.8%. Third, we develop an in-memory type conversion algorithm that leverages PIM's parallelism for efficient de-/quantization operations, alleviating pressure on CPU's vector units. Our architecture requires only 2% hardware overhead and a single new instruction, while maintaining dual functionality as both compute and storage units. Experimental evaluations using a modified gem5 simulator demonstrate that SAIL achieves up to 10.7x speedup and 19.9x higher tokens per dollar compared to ARM Neoverse-N1 CPU baselines, and up to 7.04x better cost efficiency than NVIDIA V100 GPUs, establishing a practical path for efficient CPU-based LLM inference.