# Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts

arXiv: https://arxiv.org/abs/2507.15465 · HTML: https://mlsanity.com/paper/2507.15465/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 34 of its 59 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [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)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Atom: Low-bit Quantization for Efficient and Accurate LLM Serving](https://mlsanity.com/paper/2310.19102/) (2023)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [FP8-LM: Training FP8 Large Language Models](https://mlsanity.com/paper/2310.18313/) (2023)
- [NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing](https://mlsanity.com/paper/2403.00579/) (2024)
- [Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts](https://mlsanity.com/paper/2502.19811/) (2025)
- [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)
- [PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference](https://mlsanity.com/paper/2502.07578/) (2025)

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

- [From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill](https://mlsanity.com/paper/2510.08055/) (2025)
- [Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey](https://mlsanity.com/paper/2510.00078/) (2025)
- [Rethinking Network Topologies for Cost-Effective Mixture-of-Experts LLM Serving](https://mlsanity.com/paper/2605.00254/) (2026)
- [Think Before You Grid-Search: Floor-First Triage for LLM Serving](https://mlsanity.com/paper/2607.05876/) (2026)

## Abstract (arXiv)

Computational workloads composing traditional transformer models are starkly bifurcated. Multi-Head Attention (MHA) and Grouped-Query Attention are memory-bound due to low arithmetic intensity, while FeedForward Networks are compute-bound. This dichotomy has long motivated research into specialized hardware to mitigate the attention bottleneck. This paper argues that recent architectural advances in transformer models -- Multi-head Latent Attention (MLA) and Mixture of Experts (MoE) -- introduce new dominant bottlenecks, shifting the challenge away from memory-intensive attention. We make two key observations. First, the arithmetic intensity of MLA is over two orders of magnitude higher than that of MHA, moving it toward a compute-bound regime well-matched to modern accelerators such as GPUs. Second, distributing MoE experts across a pool of accelerators allows batching to tune their arithmetic intensity to that of dense layers, producing a more balanced computational profile. Consequently, the focus of hardware and system optimization should shift from attention acceleration to high-bandwidth interconnects and balancing expert workloads across accelerators.