mlsanityData to 14 Oct 2026

MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs

arXiv 2610.17202 ↗First posted 12 Oct 2026cs.LG cs.CLcited by 0

On the map: Efficient LLM inference and serving → KV cache quantization also fits: KV cache optimization

Abstract (arXiv)

Multi-Head Latent Attention (MLA) compresses the KV cache into a latent representation, reducing inference memory and bandwidth. Existing MHA2MLA/TransMLA methods do not support QKNorm and require costly recovery on modern LLMs, especially MoE. We present MLAfication, a QKNorm-compatible, parameter-efficient extension of MHA2MLA. It combines calibrated KNorm, parameter-efficient distillation, contribution-aware Partial-RoPE, and activation-aware joint KV initialization. Across MHA and GQA models, including QKNorm- and MoE-equipped variants, MLAfication preserves performance under substantial KV-cache compression, surpasses the current SOTA on commonsense and long-context benchmarks, and extends MLA conversion to modern architectures. On Qwen3-30B-A3B, MLAfication delivers up to 5.35× the serving throughput of BF16 GQA and, combined with 4-bit KV quantization, reduces the KV-cache footprint by 94.73%. Our code is available at https://github.com/JT-Ushio/MLAfication.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in KV cache quantization, one of 12 directions in Efficient LLM inference and serving. Builds on 17 of its 23 references that are in the map. First posted on arXiv 12 Oct 2026.

Builds on

17 of 23 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference6 Feb
  2. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache5 Feb
  3. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization31 Jan

Other references · 14

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2019Root Mean Square Layer Normalizationcited by 1,480
  5. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  6. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,135
  7. 2024SnapKV: LLM Knows What You are Looking for Before Generationcited by 880
  8. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  9. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  10. 2020Query-Key Normalization for Transformerscited by 280
  11. 2024Palu: Compressing KV-Cache with Low-Rank Projectioncited by 64
  12. 2025SALS: Sparse Attention in Latent Space for KV cache Compressioncited by 11
2 more
  1. 2026VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusioncited by 6
  2. 2026Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  2. 2026Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding
  3. 2025EG-MLA: Embedding-Gated Multi-head Latent Attention for Scalable and Efficient LLMs
  4. 2025X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression
  5. 2025HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
  6. 2025KVLinC : KV Cache Quantization with Hadamard Rotation and Linear Correction
  7. 2025KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context Inference
  8. 2026OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond