LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Xinting, Luo, Junyi, Qi, Ruichen, Lei, Kauna, Laurie, Ben, Kielian, Gregory, Saligane, Mehdi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters
di: Liu, Shiwei, et al.
Pubblicazione: (2024)

HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices
di: Zhou, Ao, et al.
Pubblicazione: (2024)

MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering
di: Fayyazi, Arya, et al.
Pubblicazione: (2025)

Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity
di: Sinha, Nilotpal, et al.
Pubblicazione: (2024)

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark
di: Li, Chaojian, et al.
Pubblicazione: (2021)

LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search
di: Zhu, Hengyi, et al.
Pubblicazione: (2025)

S2-Attention: Hardware-Aware Context Sharding Among Attention Heads
di: Lin, Xihui, et al.
Pubblicazione: (2024)

Quantum-Based Self-Attention Mechanism for Hardware-Aware Differentiable Quantum Architecture Search
di: Liu, Yuxiang, et al.
Pubblicazione: (2025)

Generation of Compiler Backends from Formal Models of Hardware
di: Smith, Gus Henry
Pubblicazione: (2024)

Hardware-Aware Neural Architecture Search for Encrypted Traffic Classification on Resource-Constrained Devices
di: Chehade, Adel, et al.
Pubblicazione: (2025)

ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search
di: Nasir, Azaz-Ur-Rehman, et al.
Pubblicazione: (2025)

Mitigating Classical Resource Costs in Quantum Error Correction via Generalized qLDPC Predecoding
di: Knapen, Alexander, et al.
Pubblicazione: (2026)

Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge
di: Lu, Yao, et al.
Pubblicazione: (2024)

AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Search
di: Robben, Oscar, et al.
Pubblicazione: (2025)

HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator
di: Yu, Zhewen, et al.
Pubblicazione: (2024)

NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks
di: Gambella, Matteo, et al.
Pubblicazione: (2024)

elasticAI.explorer: Towards a Unified End-to-End Framework for Hardware-Aware Neural Architecture Search
di: Maman, Natalie, et al.
Pubblicazione: (2026)

MicroNAS: Memory and Latency Constrained Hardware-Aware Neural Architecture Search for Time Series Classification on Microcontrollers
di: King, Tobias, et al.
Pubblicazione: (2023)

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search
di: Gambella, Matteo, et al.
Pubblicazione: (2026)

NASH: Neural Architecture Search for Hardware-Optimized Machine Learning Models
di: Ji, Mengfei, et al.
Pubblicazione: (2024)

Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
di: Li, Zhengang, et al.
Pubblicazione: (2024)

DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence
di: Lv, Yang, et al.
Pubblicazione: (2025)

A Graph-Based Forensic Framework for Inferring Hardware Noise of Cloud Quantum Backend
di: Das, Subrata, et al.
Pubblicazione: (2025)

SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search
di: Bouzidi, Halima, et al.
Pubblicazione: (2024)

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA
di: Zhang, Zehuan, et al.
Pubblicazione: (2024)

EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
di: Chen, Jiyu, et al.
Pubblicazione: (2025)

TinyTNAS: GPU-Free, Time-Bound, Hardware-Aware Neural Architecture Search for TinyML Time Series Classification
di: Saha, Bidyut, et al.
Pubblicazione: (2024)

Integrated Hardware Architecture and Device Placement Search
di: Wang, Irene, et al.
Pubblicazione: (2024)

Attention Is Not Retention: The Orthogonality Constraint in Infinite-Context Architectures
di: Zahn, Oliver, et al.
Pubblicazione: (2026)

Veda: Scalable Video Diffusion via Distilled Sparse Attention
di: Han, Shihao, et al.
Pubblicazione: (2026)

SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2024)

Hardware Utilization and Inference Performance of Edge Object Detection Under Fault Injection
di: Pasandideh, Faezeh, et al.
Pubblicazione: (2026)

Quantum Circuit Simulation with Fast Tensor Decision Diagram
di: Zhang, Qirui, et al.
Pubblicazione: (2024)

NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search
di: Putra, Rachmad Vidya Wicaksana, et al.
Pubblicazione: (2024)

Hardware-Centric Analysis of DeepSeek's Multi-Head Latent Attention
di: Geens, Robin, et al.
Pubblicazione: (2025)

ArchGPT: Understanding the World's Architectures with Large Multimodal Models
di: Wang, Yuze, et al.
Pubblicazione: (2025)

Hardware-Aware DNN Compression for Homogeneous Edge Devices
di: Zhang, Kunlong, et al.
Pubblicazione: (2025)

Hardware-Aware DNN Compression for Homogeneous Edge Devices
di: Zhang, Kunlong, et al.
Pubblicazione: (2025)

Towards Automated Formal Verification of Backend Systems with LLMs
di: Xu, Kangping, et al.
Pubblicazione: (2025)

Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI
di: Thind, Parampuneet Kaur, et al.
Pubblicazione: (2026)