Imagen de Portada

Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Muru, Mishra, Mayank, Zhou, Zhongzhu, Brandon, William, Wang, Jue, Kim, Yoon, Ragan-Kelley, Jonathan, Song, Shuaiwen Leon, Athiwaratkun, Ben, Dao, Tri
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation and Language Distributed, Parallel, and Cluster Computing
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
por: Nrusimha, Aniruddha, et al.
Publicado: (2025)

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
por: Zhou, Zhongzhu, et al.
Publicado: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
por: Zhang, Zhenyu, et al.
Publicado: (2025)

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
por: Brandon, William, et al.
Publicado: (2024)

Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
por: Wang, Junlin, 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)

Mixture-of-Agents Enhances Large Language Model Capabilities
por: Wang, Junlin, et al.
Publicado: (2024)

Fast Matrix Multiplications for Lookup Table-Quantized LLMs
por: Guo, Han, et al.
Publicado: (2024)

Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
por: Thapa, Rahul, et al.
Publicado: (2024)

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation
por: He, Linda, et al.
Publicado: (2025)

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

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
por: Guo, Wentao, et al.
Publicado: (2025)

Training-Free Activation Sparsity in Large Language Models
por: Liu, James, et al.
Publicado: (2024)

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
por: Chandra, Kartik, et al.
Publicado: (2026)

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
por: Xu, Zhen, et al.
Publicado: (2025)

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

How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
por: Thapa, Rahul, et al.
Publicado: (2025)

Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets
por: Barbu, Eduard, et al.
Publicado: (2025)

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

Energy efficiency optimization of task-parallel codes on asymmetric architectures
por: Costero, Luis, et al.
Publicado: (2024)

More efficient sifting for grid norms, and applications to multiparty communication complexity
por: Kelley, Zander, et al.
Publicado: (2025)

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch
por: Douillard, Arthur, et al.
Publicado: (2025)

Guided Optimization for Image Processing Pipelines
por: Ikarashi, Yuka, et al.
Publicado: (2021)

Visual moral inference and communication
por: Zhu, Warren, et al.
Publicado: (2025)

Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation
por: Caren, Matthew, et al.
Publicado: (2024)

BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference
por: Nguyen, Van Thien, et al.
Publicado: (2025)

Meschers: Geometry Processing of Impossible Objects
por: Dodik, Ana, et al.
Publicado: (2026)

Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
por: Wang, Junlin, et al.
Publicado: (2024)

Dissociating model architectures from inference computations
por: Sajid, Noor, et al.
Publicado: (2025)

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

Cost-aware simulation-based inference
por: Bharti, Ayush, et al.
Publicado: (2024)

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
por: Nrusimha, Aniruddha, et al.
Publicado: (2024)

Measuring Sustainability Intention of ESG Fund Disclosure using Few-Shot Learning
por: Singh, Mayank, et al.
Publicado: (2024)

Towards single-shot coherent imaging via overlap-free ptychography
por: Hoidn, Oliver, et al.
Publicado: (2026)

Target-aware Bayesian inference via generalized thermodynamic integration
por: Llorente, F., et al.
Publicado: (2025)

Disentangling Reasoning and Knowledge in Medical Large Language Models
por: Thapa, Rahul, et al.
Publicado: (2025)

Large-Scale Data Selection for Instruction Tuning
por: Ivison, Hamish, et al.
Publicado: (2025)

Empathy in Explanation
por: Collins, Katherine M., et al.
Publicado: (2025)

Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient
por: Zhou, Zhongzhu, et al.
Publicado: (2025)

A parallel implementation of reduced-order modeling of large-scale systems
por: Farcas, Ionut-Gabriel, et al.
Publicado: (2025)