# TransMLA: Multi-Head Latent Attention Is All You Need

arXiv: https://arxiv.org/abs/2502.07864 · HTML: https://mlsanity.com/paper/2502.07864/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model](https://mlsanity.com/paper/2502.02737/) (2025)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [MiniCache: KV Cache Compression in Depth Dimension for Large Language Models](https://mlsanity.com/paper/2405.14366/) (2024)
- [LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference](https://mlsanity.com/paper/2407.14057/) (2024)
- [Tensor Product Attention Is All You Need](https://mlsanity.com/paper/2501.06425/) (2025)
- [MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding](https://mlsanity.com/paper/2406.09297/) (2024)
- [A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder](https://mlsanity.com/paper/2407.20485/) (2024)

## Built on by (most cited first, 23 of 23)

- [SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass](https://mlsanity.com/paper/2602.06358/) (2026)
- [Reasoning Beyond Limits: Advances and Open Problems for LLMs](https://mlsanity.com/paper/2503.22732/) (2025)
- [MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing](https://mlsanity.com/paper/2506.02006/) (2025)
- [VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion](https://mlsanity.com/paper/2605.30351/) (2026)
- [Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale](https://mlsanity.com/paper/2606.15079/) (2026)
- [CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention](https://mlsanity.com/paper/2603.17946/) (2026)
- [MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing](https://mlsanity.com/paper/2506.07366/) (2025)
- [EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction](https://mlsanity.com/paper/2603.22910/) (2026)
- [BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers](https://mlsanity.com/paper/2507.03117/) (2025)
- [xLLM Technical Report](https://mlsanity.com/paper/2510.14686/) (2025)
- [Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2510.17098/) (2025)
- [Tucker Attention: A generalization of approximate attention mechanisms](https://mlsanity.com/paper/2603.30033/) (2026)
- [Latent Multi-Head Attention for Small Language Models](https://mlsanity.com/paper/2506.09342/) (2025)
- [Multi-Head Low-Rank Attention](https://mlsanity.com/paper/2603.02188/) (2026)
- [Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion](https://mlsanity.com/paper/2604.05688/) (2026)
- [A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention](https://mlsanity.com/paper/2507.09394/) (2025)
- [TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference](https://mlsanity.com/paper/2508.15881/) (2025)
- [Joint Encoding of KV-Cache Blocks for Scalable LLM Serving](https://mlsanity.com/paper/2601.03067/) (2026)
- [The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures](https://mlsanity.com/paper/2605.11999/) (2026)
- [SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding](https://mlsanity.com/paper/2608.07915/) (2026)
- [KV-Kaizen: Learning Context-Adaptive Cache Compression Choices](https://mlsanity.com/paper/2609.37988/) (2026)
- [The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends](https://mlsanity.com/paper/2609.39661/) (2026)
- [Hybrid Latent Attention for Looped Language Models](https://mlsanity.com/paper/2610.07940/) (2026)

## Abstract (arXiv)

In this paper, we present TransMLA, a framework that seamlessly converts any GQA-based pre-trained model into an MLA-based model. Our approach enables direct compatibility with DeepSeek's codebase, allowing these models to fully leverage DeepSeek-specific optimizations such as vLLM and SGlang. By compressing 93% of the KV cache in LLaMA-2-7B, TransMLA achieves a 10.6x inference speedup at an 8K context length while preserving meaningful output quality. Additionally, the model requires only 6 billion tokens for fine-tuning to regain performance on par with the original across multiple benchmarks. TransMLA offers a practical solution for migrating GQA-based models to the MLA structure. When combined with DeepSeek's advanced features, such as FP8 quantization and Multi-Token Prediction, even greater inference acceleration can be realized.