# FlexPosit: Tunable Fractional Precision for LLM Inference Accelerators

arXiv: https://arxiv.org/abs/2609.04724 · HTML: https://mlsanity.com/paper/2609.04724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 53 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [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)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers](https://mlsanity.com/paper/2206.01861/) (2022)
- [Microscaling Data Formats for Deep Learning](https://mlsanity.com/paper/2310.10537/) (2023)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference](https://mlsanity.com/paper/2005.03842/) (2020)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2405.14917/) (2024)
- [Training Transformers with 4-bit Integers](https://mlsanity.com/paper/2306.11987/) (2023)
- [Optimizing Large Language Model Training Using FP4 Quantization](https://mlsanity.com/paper/2501.17116/) (2025)
- [ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization](https://mlsanity.com/paper/2208.14286/) (2022)
- [APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models](https://mlsanity.com/paper/2402.14866/) (2024)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation](https://mlsanity.com/paper/2403.06408/) (2024)
- [BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration](https://mlsanity.com/paper/2411.11745/) (2024)
- [FIT: A Metric for Model Sensitivity](https://mlsanity.com/paper/2210.08502/) (2022)
- [Mixed-Precision Quantization for Language Models: Techniques and Prospects](https://mlsanity.com/paper/2510.16805/) (2025)
- [The Accuracy and Efficiency of Posit Arithmetic](https://mlsanity.com/paper/2109.08225/) (2021)

## Abstract (arXiv)

Large language models (LLMs) offer remarkable capabilities but impose prohibitive compute and energy costs. Quantization governs the trade-offs between accuracy and hardware efficiency across granularity and bit-width. Finer granularity (e.g., group-wise) provides high accuracy but incurs scaling and control overhead, while coarser granularity (e.g., channel-wise) has lower overhead but loses accuracy at low precision. Meanwhile, mixed-precision quantization exposes rich accuracy-efficiency trade-offs algorithmically, but existing LLM accelerators remain limited to discrete precision modes, leaving the fractional design space between them unexplored. FlexPosit bridges these gaps through co-design of Posit-based quantization and a precision-tunable bit-serial architecture. Algorithmically, FlexPosit employs distribution-aware quantization with hardware-aligned, sensitivity-guided mixed-precision allocation, leveraging the Posit format's tapered precision to achieve group-wise-like accuracy with channel-wise-like regularity. Architecturally, FlexPosit is a unified bit-serial systolic array with lightweight per-column decoders, unified Processing Elements (PEs), and a global precision controller, enabling tunable fractional precision while preserving fully regular systolic dataflow. Across diverse LLMs, FlexPosit achieves near-FP16 accuracy with sub-5-bit fractional weights. It achieves 1.8x higher throughput and 1.2x lower energy than BitMoD (group-wise quantization), and 1.5x higher throughput and 2.0x lower energy than OliVe (channel-wise quantization), establishing a new Pareto frontier for precision-tunable LLM acceleration.