Cover Image

H2EAL: Hybrid-Bonding Architecture with Hybrid Sparse Attention for Efficient Long-Context LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fu, Zizhuo, Guo, Xiaotian, Zeng, Wenxuan, Zhong, Shuzhang, Zhang, Yadong, Chen, Peiyu, Wang, Runsheng, Ye, Le, Li, Meng
Format:	Preprint
Published:	2025
Subjects:	Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HD-MoE: Hybrid and Dynamic Parallelism for Mixture-of-Expert LLMs with 3D Near-Memory Processing
by: Huang, Haochen, et al.
Published: (2025)

An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference
by: Yao, Feiyu, et al.
Published: (2026)

Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse
by: Fu, Zizhuo, et al.
Published: (2026)

HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
by: Lin, Mao, et al.
Published: (2026)

Explainable Port Mapping Inference with Sparse Performance Counters for AMD's Zen Architectures
by: Ritter, Fabian, et al.
Published: (2024)

PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization
by: Xu, Tianshi, et al.
Published: (2024)

SparseInfer: Training-free Prediction of Activation Sparsity for Fast LLM Inference
by: Shin, Jiho, et al.
Published: (2024)

MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
by: Chu, Kexin, et al.
Published: (2026)

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
by: Yang, Shang, et al.
Published: (2025)

GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference
by: Ziller, Thomas, et al.
Published: (2026)

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
by: Zhong, Shuzhang, et al.
Published: (2025)

Statistical Modeling and Uncertainty Estimation of LLM Inference Systems
by: Ray, Kaustabha, et al.
Published: (2025)

Block Sparse Flash Attention
by: Ohayon, Daniel, et al.
Published: (2025)

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
by: Lee, Younjoo, et al.
Published: (2026)

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
by: Zhang, Jintao, et al.
Published: (2025)

SparseX: Efficient Segment-Level KV Cache Sharing for Interleaved LLM Serving
by: Zhang, Quqing, et al.
Published: (2026)

Efficient Hybrid Amplitude-Phase Quantization for Multi-Antenna Relay System
by: Kim, Changdae, et al.
Published: (2025)

Characterize LSM-tree Compaction Performance via On-Device LLM Inference
by: Ding, Jiabiao, et al.
Published: (2026)

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference
by: Hamadanian, Pouya, et al.
Published: (2025)

Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU
by: Jiang, Jevin, et al.
Published: (2026)

Architectural Trade-offs in the Energy-Efficient Era: A Comparative Study of power-capping NVIDIA H100 and H200
by: Ujeniya, Aditya, et al.
Published: (2026)

LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind
by: Zhang, Li, et al.
Published: (2025)

An Inquiry into Datacenter TCO for LLM Inference with FP8
by: Kim, Jiwoo, et al.
Published: (2025)

Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques
by: Tomczak, Nathaniel, et al.
Published: (2025)

oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation
by: Li, Jianhui, et al.
Published: (2023)

KVDirect: Distributed Disaggregated LLM Inference
by: Chen, Shiyang, et al.
Published: (2024)

Reducing Waiting Time for Medical Tourists Through Hybrid Agent-Based and Discrete-Event Simulation: A Hospital Case Study
by: Baghi, Melika, et al.
Published: (2026)

Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
by: Vellaisamy, Prabhu, et al.
Published: (2025)

AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention
by: Stankovic, Aleksandar
Published: (2025)

FlashOmni: A Unified Sparse Attention Engine for Diffusion Transformers
by: Qiao, Liang, et al.
Published: (2025)

A Novel Hybrid Optical and STAR IRS System for NTN Communications
by: Shang, Shunyuan, et al.
Published: (2025)

SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference
by: Cavagna, Hiari Pizzini, et al.
Published: (2026)

Fast Entropy Decoding for Sparse MVM on GPUs
by: Schätzle, Emil, et al.
Published: (2026)

PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
by: An, Zihao, et al.
Published: (2025)

Faster LLM Inference using DBMS-Inspired Preemption and Cache Replacement Policies
by: Kim, Kyoungmin, et al.
Published: (2024)

Accelerating LLM Inference via Dynamic KV Cache Placement in Heterogeneous Memory System
by: Fang, Yunhua, et al.
Published: (2025)

AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism
by: Gupta, Ahan, et al.
Published: (2026)

Architecture Specific Generation of Large Scale Lattice Boltzmann Methods for Sparse Complex Geometries
by: Suffa, Philipp, et al.
Published: (2024)

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis
by: Cheng, Long, et al.
Published: (2025)

DeepContext: A Context-aware, Cross-platform, and Cross-framework Tool for Performance Profiling and Analysis of Deep Learning Workloads
by: Zhao, Qidong, et al.
Published: (2024)