# Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs

arXiv: https://arxiv.org/abs/2403.20041 · HTML: https://mlsanity.com/paper/2403.20041/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time](https://mlsanity.com/paper/2310.17157/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [LLM-FP4: 4-Bit Floating-Point Quantized Transformers](https://mlsanity.com/paper/2310.16836/) (2023)
- [QAQ: Quality Adaptive Quantization for LLM KV Cache](https://mlsanity.com/paper/2403.04643/) (2024)
- [MNN: A Universal and Efficient Inference Engine](https://mlsanity.com/paper/2002.12418/) (2020)
- [ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats](https://mlsanity.com/paper/2307.09782/) (2023)
- [Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference](https://mlsanity.com/paper/2006.03031/) (2020)

## Built on by (most cited first, 17 of 17)

- [Small Language Models: Survey, Measurements, and Insights](https://mlsanity.com/paper/2409.15790/) (2024)
- [PowerInfer-2: Fast Large Language Model Inference on a Smartphone](https://mlsanity.com/paper/2406.06282/) (2024)
- [Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity](https://mlsanity.com/paper/2406.02913/) (2024)
- [BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices](https://mlsanity.com/paper/2411.10640/) (2024)
- [WDMoE: Wireless Distributed Large Language Models with Mixture of Experts](https://mlsanity.com/paper/2405.03131/) (2024)
- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Execution](https://mlsanity.com/paper/2510.15312/) (2025)
- [MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores](https://mlsanity.com/paper/2504.16786/) (2025)
- [AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model](https://mlsanity.com/paper/2510.11496/) (2025)
- [LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load](https://mlsanity.com/paper/2603.23640/) (2026)
- [Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference](https://mlsanity.com/paper/2505.06461/) (2025)
- [Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey](https://mlsanity.com/paper/2601.03181/) (2026)
- [Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants](https://mlsanity.com/paper/2508.16070/) (2025)
- [Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigation](https://mlsanity.com/paper/2510.19498/) (2025)
- [MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning](https://mlsanity.com/paper/2508.01540/) (2025)
- [EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs](https://mlsanity.com/paper/2609.06551/) (2026)
- [TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching](https://mlsanity.com/paper/2609.21172/) (2026)

## Abstract (arXiv)

The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones. However, the current methods for on-device LLM deployment maintain slow inference speed, which causes poor user experience. To facilitate high-efficiency LLM deployment on device GPUs, we propose four optimization techniques: (a) a symbolic expression-based approach to support dynamic shape model inference; (b) operator optimizations and execution priority setting to enhance inference speed and reduce phone lagging; (c) an FP4 quantization method termed M0E4 to reduce dequantization overhead; (d) a sub-tensor-based technique to eliminate the need for copying KV cache after LLM inference. Furthermore, we implement these methods in our mobile inference engine, Transformer-Lite, which is compatible with both Qualcomm and MTK processors. We evaluated Transformer-Lite's performance using LLMs with varied architectures and parameters ranging from 2B to 14B. Specifically, we achieved prefill and decoding speeds of 121 token/s and 14 token/s for ChatGLM2 6B, and 330 token/s and 30 token/s for smaller Gemma 2B, respectively. Compared with CPU-based FastLLM and GPU-based MLC-LLM, our engine attains over 10x speedup for the prefill speed and 2~3x speedup for the decoding speed.