Image de couverture de livre

MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ramachandran, Akshat, Kundu, Souvik, Krishna, Tushar
Format:	Preprint
Publié:	2024
Sujets:	Hardware Architecture Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
par: Ramachandran, Akshat, et autres
Publié: (2025)

AIRCHITECT v2: Learning the Hardware Accelerator Design Space through Unified Representations
par: Seo, Jamin, et autres
Publié: (2025)

Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference
par: Ramachandran, Akshat, et autres
Publié: (2024)

OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models
par: Koo, Jahyun, et autres
Publié: (2024)

Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators
par: Jeong, Geonhwa, et autres
Publié: (2024)

FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
par: Qiao, Ye, et autres
Publié: (2026)

TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
par: Kang, Hao, et autres
Publié: (2024)

On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
par: Huang, Wei, et autres
Publié: (2023)

Precision-Scalable Microscaling Datapaths with Optimized Reduction Tree for Efficient NPU Integration
par: Cuyckens, Stef, et autres
Publié: (2025)

Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators
par: Kim, Jiyoon, et autres
Publié: (2025)

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
par: Bambhaniya, Abhimanyu, et autres
Publié: (2024)

Improving Quantization with Post-Training Model Expansion
par: Franco, Giuseppe, et autres
Publié: (2025)

Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns
par: Bambhaniya, Abhimanyu, et autres
Publié: (2026)

ALADIN: Accuracy-Latency-Aware Design-space Inference Analysis for Embedded AI Accelerators
par: Baldi, T., et autres
Publié: (2026)

SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization
par: Xie, Rui, et autres
Publié: (2024)

Late Breaking Results: Quamba-SE: Soft-edge Quantizer for Activations in State Space Models
par: Chen, Yizhi, et autres
Publié: (2026)

NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI
par: Yang, Hanchen, et autres
Publié: (2025)

Characterization and Mitigation of Training Instabilities in Microscaling Formats
par: Su, Huangyuan, et autres
Publié: (2025)

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference
par: Bambhaniya, Abhimanyu Rajeshkumar, et autres
Publié: (2025)

Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers
par: Lu, Jinming, et autres
Publié: (2025)

Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores
par: Ma, Shaobo, et autres
Publié: (2024)

MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
par: Zhang, Yu, et autres
Publié: (2024)

AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization
par: Matsushima, Kosuke, et autres
Publié: (2026)

Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications
par: Abushahla, Hamza A., et autres
Publié: (2025)

Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction
par: Chhugani, Jatin, et autres
Publié: (2026)

RESQ: A Unified Framework for REliability- and Security Enhancement of Quantized Deep Neural Networks
par: Mohammadi, Ali Soltan, et autres
Publié: (2026)

MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving
par: Lee, Jungi, et autres
Publié: (2025)

GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units
par: Das, Arghadip, et autres
Publié: (2025)

Heterogeneous Acceleration Pipeline for Recommendation System Training
par: Adnan, Muhammad, et autres
Publié: (2022)

AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology
par: Cong, Rongqing, et autres
Publié: (2024)

LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
par: Lin, Yujun, et autres
Publié: (2025)

Mirage: An RNS-Based Photonic Accelerator for DNN Training
par: Demirkiran, Cansu, et autres
Publié: (2023)

REASON: Accelerating Probabilistic Logical Reasoning for Scalable Neuro-Symbolic Intelligence
par: Wan, Zishen, et autres
Publié: (2026)

Differentiable Initialization-Accelerated CPU-GPU Hybrid Combinatorial Scheduling
par: Liu, Mingju, et autres
Publié: (2026)

The Role of Advanced Computer Architectures in Accelerating Artificial Intelligence Workloads
par: Amin, Shahid, et autres
Publié: (2025)

FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs
par: Kabir, Ehsan, et autres
Publié: (2024)

AutoHLS: Learning to Accelerate Design Space Exploration for HLS Designs
par: Ahmed, Md Rubel, et autres
Publié: (2024)

TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators
par: Meng, Chang, et autres
Publié: (2026)

Enabling Physical AI at the Edge: Hardware-Accelerated Recovery of System Dynamics
par: Xu, Bin, et autres
Publié: (2025)

MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs
par: Gong, Junfeng, et autres
Publié: (2024)