Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Muru, Mishra, Mayank, Zhou, Zhongzhu, Brandon, William, Wang, Jue, Kim, Yoon, Ragan-Kelley, Jonathan, Song, Shuaiwen Leon, Athiwaratkun, Ben, Dao, Tri
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language Distributed, Parallel, and Cluster Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FlashFormer: Whole-Model Kernels for Efficient Low-Batch Inference
par: Nrusimha, Aniruddha, et autres
Publié: (2025)

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
par: Zhou, Zhongzhu, et autres
Publié: (2026)

Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
par: Zhang, Zhenyu, et autres
Publié: (2025)

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
par: Brandon, William, et autres
Publié: (2024)

Improving Model Alignment Through Collective Intelligence of Open-Source LLMS
par: Wang, Junlin, et autres
Publié: (2025)

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
par: Jia, Jinda, et autres
Publié: (2026)

Mixture-of-Agents Enhances Large Language Model Capabilities
par: Wang, Junlin, et autres
Publié: (2024)

Fast Matrix Multiplications for Lookup Table-Quantized LLMs
par: Guo, Han, et autres
Publié: (2024)

Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models
par: Thapa, Rahul, et autres
Publié: (2024)

Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation
par: He, Linda, et autres
Publié: (2025)

Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
par: Maheswaran, Monishwaran, et autres
Publié: (2026)

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
par: Guo, Wentao, et autres
Publié: (2025)

Training-Free Activation Sparsity in Large Language Models
par: Liu, James, et autres
Publié: (2024)

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
par: Chandra, Kartik, et autres
Publié: (2026)

When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
par: Xu, Zhen, et autres
Publié: (2025)

Hardware-Efficient Attention for Fast Decoding
par: Zadouri, Ted, et autres
Publié: (2025)

How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
par: Thapa, Rahul, et autres
Publié: (2025)

Improving Estonian Text Simplification through Pretrained Language Models and Custom Datasets
par: Barbu, Eduard, et autres
Publié: (2025)

CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
par: Zhou, Zhongzhu, et autres
Publié: (2026)

Energy efficiency optimization of task-parallel codes on asymmetric architectures
par: Costero, Luis, et autres
Publié: (2024)

More efficient sifting for grid norms, and applications to multiparty communication complexity
par: Kelley, Zander, et autres
Publié: (2025)

Guided Optimization for Image Processing Pipelines
par: Ikarashi, Yuka, et autres
Publié: (2021)

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch
par: Douillard, Arthur, et autres
Publié: (2025)

Visual moral inference and communication
par: Zhu, Warren, et autres
Publié: (2025)

Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation
par: Caren, Matthew, et autres
Publié: (2024)

BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference
par: Nguyen, Van Thien, et autres
Publié: (2025)

Meschers: Geometry Processing of Impossible Objects
par: Dodik, Ana, et autres
Publié: (2026)

Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategies
par: Wang, Junlin, et autres
Publié: (2024)

Introspective Diffusion Language Models
par: Yu, Yifan, et autres
Publié: (2026)

Dissociating model architectures from inference computations
par: Sajid, Noor, et autres
Publié: (2025)

Cost-aware simulation-based inference
par: Bharti, Ayush, et autres
Publié: (2024)

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
par: Nrusimha, Aniruddha, et autres
Publié: (2024)

Measuring Sustainability Intention of ESG Fund Disclosure using Few-Shot Learning
par: Singh, Mayank, et autres
Publié: (2024)

Towards single-shot coherent imaging via overlap-free ptychography
par: Hoidn, Oliver, et autres
Publié: (2026)

Disentangling Reasoning and Knowledge in Medical Large Language Models
par: Thapa, Rahul, et autres
Publié: (2025)

Target-aware Bayesian inference via generalized thermodynamic integration
par: Llorente, F., et autres
Publié: (2025)

Large-Scale Data Selection for Instruction Tuning
par: Ivison, Hamish, et autres
Publié: (2025)

Empathy in Explanation
par: Collins, Katherine M., et autres
Publié: (2025)

Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient
par: Zhou, Zhongzhu, et autres
Publié: (2025)

A parallel implementation of reduced-order modeling of large-scale systems
par: Farcas, Ionut-Gabriel, et autres
Publié: (2025)