# Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion

arXiv: https://arxiv.org/abs/2605.12825 · HTML: https://mlsanity.com/paper/2605.12825/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [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)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Dream 7B: Diffusion Large Language Models](https://mlsanity.com/paper/2508.15487/) (2025)
- [Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models](https://mlsanity.com/paper/2503.09573/) (2025)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Mercury: Ultra-Fast Language Models Based on Diffusion](https://mlsanity.com/paper/2506.17298/) (2025)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [dKV-Cache: The Cache for Diffusion Language Models](https://mlsanity.com/paper/2505.15781/) (2025)
- [Fast-dLLM v2: Efficient Block-Diffusion LLM](https://mlsanity.com/paper/2509.26328/) (2025)
- [DFlash: Block Diffusion for Flash Speculative Decoding](https://mlsanity.com/paper/2602.06036/) (2026)
- [SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation](https://mlsanity.com/paper/2510.06303/) (2025)
- [Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference](https://mlsanity.com/paper/2403.09054/) (2024)
- [FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling](https://mlsanity.com/paper/2603.05451/) (2026)
- [dParallel: Learnable Parallel Decoding for dLLMs](https://mlsanity.com/paper/2509.26488/) (2025)
- [ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer](https://mlsanity.com/paper/2412.07720/) (2024)
- [Block Transformer: Global-to-Local Language Modeling for Fast Inference](https://mlsanity.com/paper/2406.02657/) (2024)
- [LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation](https://mlsanity.com/paper/2501.05414/) (2025)
- [From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs](https://mlsanity.com/paper/2512.06776/) (2025)
- [Set Block Decoding is a Language Model Inference Accelerator](https://mlsanity.com/paper/2509.04185/) (2025)
- [dLLM: Simple Diffusion Language Modeling](https://mlsanity.com/paper/2602.22661/) (2026)

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

- [FLARE: Diffusion for Hybrid Language Model](https://mlsanity.com/paper/2606.01774/) (2026)
- [H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache](https://mlsanity.com/paper/2609.24197/) (2026)
- [Evaluating Losslessness in Speculative Decoding Under Finite-Precision Inference](https://mlsanity.com/paper/2609.15504/) (2026)
- [LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter](https://mlsanity.com/paper/2609.37029/) (2026)

## Abstract (arXiv)

We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequential nature of standard autoregressive decoding represents a fundamental bottleneck for high-throughput inference. While diffusion language models attempt to break this barrier via parallel generation, they suffer from significant performance degradation, high training costs, and a lack of rigorous convergence guarantees. Orthrus resolves this dichotomy natively. Designed to seamlessly integrate into existing Transformers, the framework augments a frozen LLM with a lightweight, trainable module to create a parallel diffusion view alongside the standard autoregressive view. In this unified system, both views attend to the exact same high-fidelity Key-Value (KV) cache; the autoregressive head executes context pre-filling to construct accurate KV representations, while the diffusion head executes parallel generation. By employing an exact consensus mechanism between the two views, Orthrus guarantees lossless inference, delivering up to a 7.8x speedup with only an O(1) memory cache overhead and minimal parameter additions.