# TriGen: NPU Architecture for End-to-End Acceleration of Large Language Models based on SW-HW Co-Design

arXiv: https://arxiv.org/abs/2602.12962 · HTML: https://mlsanity.com/paper/2602.12962/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [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)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [Microscaling Data Formats for Deep Learning](https://mlsanity.com/paper/2310.10537/) (2023)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [With Shared Microexponents, A Little Shifting Goes a Long Way](https://mlsanity.com/paper/2302.08007/) (2023)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [Apple Intelligence Foundation Language Models: Tech Report 2025](https://mlsanity.com/paper/2507.13575/) (2025)
- [NN-LUT: Neural Approximation of Non-Linear Operations for Efficient Transformer Inference](https://mlsanity.com/paper/2112.02191/) (2021)
- [Benchmarking and Dissecting the Nvidia Hopper GPU Architecture](https://mlsanity.com/paper/2402.13499/) (2024)
- [Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference](https://mlsanity.com/paper/2501.14794/) (2025)
- [Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format](https://mlsanity.com/paper/2411.15982/) (2024)
- [eIQ Neutron: Redefining Edge-AI Inference with Integrated NPU and Compiler Innovations](https://mlsanity.com/paper/2509.14388/) (2025)
- [FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs](https://mlsanity.com/paper/2504.19746/) (2025)

## Abstract (arXiv)

Recent studies have extensively explored NPU architectures for accelerating AI inference in on-device environments, which are inherently resource-constrained. Meanwhile, transformer-based large language models (LLMs) have become dominant, with rapidly increasing model sizes but low degree of parameter reuse compared to conventional CNNs, making end-to-end execution on resource-limited devices extremely challenging. To address these challenges, we propose TriGen, a novel NPU architecture tailored for resource-constrained environments through software-hardware co-design. Firstly, TriGen adopts low-precision computation using microscaling (MX) to enable additional optimization opportunities while preserving accuracy, and resolves the issues that arise by employing such precision. Secondly, to jointly optimize both nonlinear and linear operations, TriGen eliminates the need for specialized hardware for essential nonlinear operations by using fast and accurate LUT, thereby maximizing performance gains and reducing hardware-cost in on-device environments, and finally, by taking practical hardware constraints into account, further employs scheduling techniques to maximize computational utilization even under limited on-chip memory capacity. We evaluate the performance of TriGen on various LLMs and show that TriGen achieves an average 2.73x performance speedup and 52% less memory transfer over the baseline NPU design with negligible accuracy loss.