# Hardware-Software Co-design for 3D-DRAM-based LLM Serving Accelerator

arXiv: https://arxiv.org/abs/2603.04797 · HTML: https://mlsanity.com/paper/2603.04797/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 34 of its 77 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## 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 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Online normalizer calculation for softmax](https://mlsanity.com/paper/1805.02867/) (2018)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (2024)
- [Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures](https://mlsanity.com/paper/2505.09343/) (2025)
- [Duplex: A Device for Large Language Models with Mixture of Experts, Grouped Query Attention, and Continuous Batching](https://mlsanity.com/paper/2409.01141/) (2024)
- [Ramulator 2.0: A Modern, Modular, and Extensible DRAM Simulator](https://mlsanity.com/paper/2308.11030/) (2023)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have been widely deployed for online generative services, where numerous LLM instances jointly handle workloads with fluctuating request arrival rates and variable request lengths. To efficiently execute coexisting compute-intensive and memory-intensive operators, near-memory processing (NMP) based computing paradigm has been extensively proposed. However, existing NMP designs adopt coarse-grained KV cache management and inflexible attention execution flow. Such limitations hinder these proposals from efficiently handling textithighly dynamic LLM serving workloads, limiting their ability to accelerate LLM serving. To tackle these problems, we propose Helios, a Hybrid-bonding-based ulineLLM ulineServing accelerator. Helios aims to bridge the fundamental gap between the dynamic nature of KV cache management in LLM serving and the distributed, non-uniform memory abstraction among NMP processing engines (PEs). To this end, we design both the intra-PE execution flow and the inter-PE communication primitives for distributed tiled attention execution. We further propose textitspatially-aware KV cache allocation mechanism to balance the attention workload distribution while minimizing the inter-PE data transfer overhead. Compared with existing GPU/NMP designs, Helios achieves 3.25 times (geomean) speedup and 3.36 times (geomean) better energy efficiency, along with up to 72%/76% P50/P99 time-between-tokens degradation.