# MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness

arXiv: https://arxiv.org/abs/2509.10372 · HTML: https://mlsanity.com/paper/2509.10372/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 52 of its 114 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (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)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Q8BERT: Quantized 8Bit BERT](https://mlsanity.com/paper/1910.06188/) (2019)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [WinoGrande: An Adversarial Winograd Schema Challenge at Scale](https://mlsanity.com/paper/1907.10641/) (2019)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [Accelerating LLM Inference with Staged Speculative Decoding](https://mlsanity.com/paper/2308.04623/) (2023)
- [SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks](https://mlsanity.com/paper/1708.04485/) (2017)
- [Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks](https://mlsanity.com/paper/1712.01507/) (2017)
- [A3: Accelerating Attention Mechanisms in Neural Networks with Approximation](https://mlsanity.com/paper/2002.10941/) (2020)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache](https://mlsanity.com/paper/2401.02669/) (2024)
- [EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference](https://mlsanity.com/paper/2011.14203/) (2020)
- [FTRANS: Energy-Efficient Acceleration of Transformers using FPGA](https://mlsanity.com/paper/2007.08563/) (2020)
- [DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation](https://mlsanity.com/paper/2209.10797/) (2022)

## Built on by (most cited first, 4 of 4)

- [LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure](https://mlsanity.com/paper/2602.23036/) (2026)
- [BitStopper: An Efficient Transformer Attention Accelerator via Stage-fusion and Early Termination](https://mlsanity.com/paper/2512.06457/) (2025)
- [LAPA: Log-Domain Prediction-Driven Dynamic Sparsity Accelerator for Transformer Model](https://mlsanity.com/paper/2512.07855/) (2025)
- [MOCAP: Wafer-Scale-Chip-Oriented Memory-Orchestrated Chunked Pipelining Framework for Prefill-Only LLM Inference](https://mlsanity.com/paper/2606.22968/) (2026)

## Abstract (arXiv)

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory efficient accelerator. Unfortunately, existing Transformer accelerators struggle to address both aspects simultaneously, as they focus on value-level processing, missing fine-grained opportunities to optimize computation and memory collaboratively. This paper introduces MCBP, a bit-grained compute-memory efficient algorithm-hardware co-design that leverages bit-slice (BS) enabled repetitiveness and sparsity to accelerate LLM inference. MCBP features three key innovations: 1) BS-repetitiveness-enabled computation reduction (BRCR), which eliminates redundant GEMM computations via leveraging redundancy hidden among BS vectors; 2) BS-sparsity-enabled two-state coding (BSTC), which reduces weight access via exploiting significant sparsity in high-order bit-slice weight; 3) Bit-grained progressive prediction (BGPP), which reduces KV cache access by leveraging early-termination-based bit-grained prediction. These techniques, supported by custom accelerator designs, effectively alleviate the burden in GEMM, weight access, and KV cache access. Extensive experiments on 26 benchmarks show that MCBP achieves 9.43x speed up and 31.1x higher energy efficiency than Nvidia A100 GPU. Compared to SOTA Transformer accelerators, MCBP achieves 35x, 5.2x and 3.2x energy saving than Spatten, FACT and SOFA, respectively.