# zFLoRA: Zero-Latency Fused Low-Rank Adapters

arXiv: https://arxiv.org/abs/2510.25784 · HTML: https://mlsanity.com/paper/2510.25784/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [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)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2304.01933/) (2023)
- [MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases](https://mlsanity.com/paper/2402.14905/) (2024)
- [LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning](https://mlsanity.com/paper/2308.03303/) (2023)
- [On-Device Language Models: A Comprehensive Review](https://mlsanity.com/paper/2409.00088/) (2024)
- [LoRA-Pro: Are Low-Rank Adapters Properly Optimized?](https://mlsanity.com/paper/2407.18242/) (2024)
- [Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications](https://mlsanity.com/paper/2404.13506/) (2024)
- [ResLoRA: Identity Residual Mapping in Low-Rank Adaption](https://mlsanity.com/paper/2402.18039/) (2024)

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

- [Understanding and Guiding Layer Placement in Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2602.04019/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed with task-specific adapters catering to multiple downstream applications. In such a scenario, the additional compute associated with these apparently insignificant number of adapter parameters (typically less than 1% of the base model) turns out to be disproportionately significant during inference time (upto 2.5x times that of the base model). In this paper, we propose a new zero-latency fused low-rank adapter (zFLoRA) that introduces zero or negligible latency overhead on top of the base model. Experimental results on LLMs of size 1B, 3B and 7B show that zFLoRA compares favorably against the popular supervised fine-tuning benchmarks including low-rank adapters (LoRA) as well as full fine-tuning (FFT). Experiments are conducted on 18 different tasks across three different categories namely commonsense reasoning, math reasoning and summary-dialogue. Latency measurements made on NPU (Samsung Galaxy S25+) as well as GPU (NVIDIA H100) platforms show that the proposed zFLoRA adapters introduce zero to negligible latency overhead.