# Disaggregated Quantization: Specializing LLM Prefill and Decode

arXiv: https://arxiv.org/abs/2609.26333 · HTML: https://mlsanity.com/paper/2609.26333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks](https://mlsanity.com/paper/2402.04396/) (2024)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models](https://mlsanity.com/paper/2408.11743/) (2024)
- [ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization](https://mlsanity.com/paper/2502.02631/) (2025)
- [Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization](https://mlsanity.com/paper/2509.23202/) (2025)
- [QuEST: Stable Training of LLMs with 1-Bit Weights and Activations](https://mlsanity.com/paper/2502.05003/) (2025)
- [Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery](https://mlsanity.com/paper/2601.20088/) (2026)
- [Progressive Mixed-Precision Decoding for Efficient LLM Inference](https://mlsanity.com/paper/2410.13461/) (2024)
- [INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats](https://mlsanity.com/paper/2510.25602/) (2025)
- [Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse](https://mlsanity.com/paper/2608.03893/) (2026)
- [Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs](https://mlsanity.com/paper/2506.09104/) (2025)
- [When LLMs get significantly worse: A statistical approach to detect model degradations](https://mlsanity.com/paper/2602.10144/) (2026)
- [Leech Lattice Vector Quantization for Efficient LLM Compression](https://mlsanity.com/paper/2603.11021/) (2026)
- [Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations](https://mlsanity.com/paper/2505.06653/) (2025)

## Abstract (arXiv)

Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce memory traffic during generation. We propose "disaggregated quantization" (DQ), which specializes computation formats, weights and storage placement to both of these phases. On Qwen 3 and Gemma 3, removing activation quantization specifically on decode improves accuracy on decode-heavy tasks without increasing inference cost. Training separate compute-native prefill weights accelerates prompt processing relative to weight-only inference while matching or exceeding its accuracy at 2-3-bit decode on both decode-heavy and prefill-heavy tasks. With released Qwen3.8-27B GGUF decoders, training an NVFP4 prefiller improves 1-bit accuracy by 32.5 points on MMLU-Pro and 35.3 on MMMU-Pro without modifying the decode checkpoint. To accommodate the additional checkpoint on a single device, offloaded disaggregated prefill (ODP) streams its weights from SSD, amortizing loading over prompt length. On the same 27B model, ODP delivers a 1.78x time-to-first-token speedup over the weight-only baseline at 8K prompt length in llama.cpp. We evaluate accuracy under disaggregated serving in vLLM and further validate shared-weight format disaggregation through post-training quantization on models up to 2.8T parameters.