# AxLLM: accelerator architecture for large language models with computation reuse capability

arXiv: https://arxiv.org/abs/2509.22512 · HTML: https://mlsanity.com/paper/2509.22512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Accurate LoRA-Finetuning Quantization of LLMs via Information Retention](https://mlsanity.com/paper/2402.05445/) (2024)
- [Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism](https://mlsanity.com/paper/2406.03853/) (2024)
- [ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization](https://mlsanity.com/paper/2406.05981/) (2024)
- [LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference](https://mlsanity.com/paper/2408.06003/) (2024)
- [Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization](https://mlsanity.com/paper/2503.18599/) (2025)
- [AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems](https://mlsanity.com/paper/2301.09262/) (2023)

## Abstract (arXiv)

Large language models demand massive computational power and memory resources, posing significant challenges for efficient deployment. While quantization has been widely explored to reduce model size and computation, this paper demonstrates an additional benefit: quantization increases parameter locality, creating opportunities for computation reuse. Building on this insight, we propose AxLLM, a hardware accelerator architecture designed for quantized models. Axllm introduces a novel redundancy elimination technique that caches and reuses multiplication results for repeated weight values, substantially reducing redundant operations. The architecture features dual multiply and reuse pipelines, efficiently supporting both base models and LoRA fine-tuned models without altering parameters, retraining, or requiring offline preprocessing. Experimental results show that AxLLM achieves up to 90% reduction in computations, delivering 28% lower energy consumption and a 1.7x speedup over baseline execution. These results highlight Axllm as a scalable and efficient solution for accelerating LLMs on specialized hardware.