Image de couverture de livre

LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Chenkai, Jin, Yijie, Li, Jiajun, Tu, Yi, Long, Guoping, Tu, Dandan, Song, Mingcong, Si, Hongjie, Hou, Tianqi, Yan, Junchi, Deng, Zhijie
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
par: Zhang, Haohui, et autres
Publié: (2026)

Scaling Speculative Decoding with Lookahead Reasoning
par: Fu, Yichao, et autres
Publié: (2025)

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
par: Wu, Chengyue, et autres
Publié: (2025)

Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
par: Wang, Xu, et autres
Publié: (2025)

UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
par: Xu, Chenkai, et autres
Publié: (2025)

Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels
par: Song, Mingcong, et autres
Publié: (2024)

LightningRL: Breaking the Accuracy-Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning
par: Hu, Yanzhe, et autres
Publié: (2026)

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
par: Xiao, Zhongyu, et autres
Publié: (2026)

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
par: Fu, Yichao, et autres
Publié: (2024)

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing
par: Long, Lingkun, et autres
Publié: (2026)

dLLM: Simple Diffusion Language Modeling
par: Zhou, Zhanhui, et autres
Publié: (2026)

ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
par: Zhu, Zijian, et autres
Publié: (2026)

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
par: Huang, Jianuo, et autres
Publié: (2025)

Constrained Decoding with Speculative Lookaheads
par: Nakshatri, Nishanth, et autres
Publié: (2024)

DeepPrune: Parallel Scaling without Inter-trace Redundancy
par: Tu, Shangqing, et autres
Publié: (2025)

Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
par: Lei, Yu, et autres
Publié: (2025)

AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size
par: Lu, Guanxi, et autres
Publié: (2025)

Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs
par: Wang, Xinzhong, et autres
Publié: (2026)

Fast-dLLM v2: Efficient Block-Diffusion LLM
par: Wu, Chengyue, et autres
Publié: (2025)

Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
par: Song, Yuerong, et autres
Publié: (2025)

dParallel: Learnable Parallel Decoding for dLLMs
par: Chen, Zigeng, et autres
Publié: (2025)

dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
par: Liu, Zhiyuan, et autres
Publié: (2025)

Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs
par: Wu, Junyi, et autres
Publié: (2026)

Scene-Aware Memory Discrimination: Deciding Which Personal Knowledge Stays
par: Zhong, Yijie, et autres
Publié: (2026)

In-context KV-Cache Eviction for LLMs via Attention-Gate
par: Zeng, Zihao, et autres
Publié: (2024)

Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
par: Hu, Lanxiang, et autres
Publié: (2025)

dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
par: Tian, Wenjie, et autres
Publié: (2026)

Adaptive Prototype Model for Attribute-based Multi-label Few-shot Action Recognition
par: Xiao, Juefeng, et autres
Publié: (2025)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
par: Lee, Sanghyun, et autres
Publié: (2025)

LINOCS: Lookahead Inference of Networked Operators for Continuous Stability
par: Mudrik, Noga, et autres
Publié: (2024)

Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation
par: Long, Jianzhi, et autres
Publié: (2025)

Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models
par: Mamou, Jonathan, et autres
Publié: (2024)

Sample-Efficient "Clustering and Conquer" Procedures for Parallel Large-Scale Ranking and Selection
par: Zhang, Zishi, et autres
Publié: (2024)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
par: Zhang, Tianao, et autres
Publié: (2025)

DMax: Aggressive Parallel Decoding for dLLMs
par: Chen, Zigeng, et autres
Publié: (2026)

Parallel Continuous Chain-of-Thought with Jacobi Iteration
par: Wu, Haoyi, et autres
Publié: (2025)

Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
par: Luo, Jiajun, et autres
Publié: (2024)

TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval
par: Lin, Chien-Yu, et autres
Publié: (2025)

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
par: Du, Zhenbang, et autres
Publié: (2026)

Accelerating Transformer Inference for Translation via Parallel Decoding
par: Santilli, Andrea, et autres
Publié: (2023)