Imagen de Portada

Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Oncescu, Costin-Andrei, Wu, Qingyang, Chung, Wai Tong, Wu, Robert, Gopal, Bryan, Wang, Junxiong, Dao, Tri, Athiwaratkun, Ben
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling
por: Meterez, Alexandru, et al.
Publicado: (2025)

Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
por: Shao, Zelei, et al.
Publicado: (2025)

The Recurrent Transformer: Greater Effective Depth and Efficient Decoding
por: Oncescu, Costin-Andrei, et al.
Publicado: (2026)

Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond
por: Oncescu, Costin-Andrei, et al.
Publicado: (2024)

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
por: Xu, Zhiyuan, et al.
Publicado: (2026)

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
por: Zhou, Yixiao, et al.
Publicado: (2025)

A Simplified Analysis of SGD for Linear Regression with Weight Averaging
por: Meterez, Alexandru, et al.
Publicado: (2025)

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference
por: Vankov, Daniil, et al.
Publicado: (2026)

SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
por: Wu, Juntong, et al.
Publicado: (2026)

Feature emergence via margin maximization: case studies in algebraic tasks
por: Morwani, Depen, et al.
Publicado: (2023)

Introspective Diffusion Language Models
por: Yu, Yifan, et al.
Publicado: (2026)

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline
por: Fang, Zhiyuan, et al.
Publicado: (2025)

Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models
por: Wu, Qiong, et al.
Publicado: (2024)

BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
por: Wu, Juntong, et al.
Publicado: (2026)

CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
por: Wang, Yucheng, et al.
Publicado: (2026)

Opportunistic Routing in Wireless Communications via Learnable State-Augmented Policies
por: Das, Sourajit, et al.
Publicado: (2025)

Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts
por: Yang, Jin, et al.
Publicado: (2025)

Speculative Speculative Decoding
por: Kumar, Tanishq, et al.
Publicado: (2026)

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
por: Wang, Junxiong, et al.
Publicado: (2026)

CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
por: Zhou, Zhongzhu, et al.
Publicado: (2026)

Hardware-Efficient Attention for Fast Decoding
por: Zadouri, Ted, et al.
Publicado: (2025)

Expert Routing with Synthetic Data for Continual Learning
por: Byun, Yewon, et al.
Publicado: (2024)

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
por: Chai, Ziwei, et al.
Publicado: (2024)

Data Diversification Methods In Alignment Enhance Math Performance In LLMs
por: Dokmeci, Berkan, et al.
Publicado: (2025)

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
por: Jia, Jinda, et al.
Publicado: (2026)

Search Your Block Floating Point Scales!
por: Gupta, Tanmaey, et al.
Publicado: (2026)

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
por: Zhou, Yifan, et al.
Publicado: (2025)

MoxE: Mixture of xLSTM Experts with Entropy-Aware Routing for Efficient Language Modeling
por: Thiombiano, Abdoul Majid O., et al.
Publicado: (2025)

The Mamba in the Llama: Distilling and Accelerating Hybrid Models
por: Wang, Junxiong, et al.
Publicado: (2024)

RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
por: Liang, Jiacheng, et al.
Publicado: (2026)

Soft Task-Aware Routing of Experts for Equivariant Representation Learning
por: Jeon, Jaebyeong, et al.
Publicado: (2025)

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
por: Maheswaran, Monishwaran, et al.
Publicado: (2026)

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
por: Liu, Baihui, et al.
Publicado: (2026)

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
por: Wang, Qingyue, et al.
Publicado: (2025)

Geometric Routing Enables Causal Expert Control in Mixture of Experts
por: Ternovtsii, Ivan, et al.
Publicado: (2026)

Routing-Free Mixture-of-Experts
por: Liu, Yilun, et al.
Publicado: (2026)

Multilingual Routing in Mixture-of-Experts
por: Bandarkar, Lucas, et al.
Publicado: (2025)

Route Experts by Sequence, not by Token
por: Wen, Tiansheng, et al.
Publicado: (2025)

Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference
por: Han, Ziyi, et al.
Publicado: (2025)

Cross-Platform Fused MoE Dispatch in Triton: Portable Expert Routing Without CUDA
por: Mitra, Subhadip
Publicado: (2026)