hardware-aware

Tag

Cards List
#hardware-aware

Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts

arXiv cs.LG · 2026-08-12 Cached

This paper introduces MOSAIC, a framework that jointly optimizes sparse Mixture-of-Experts model architecture and hardware systems for large-scale pretraining, showing that compute-optimal sparsity is not necessarily cluster-optimal when MFU, communication costs, and parallel layouts are considered.

0 favorites 0 likes
#hardware-aware

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

arXiv cs.LG · 2026-07-10 Cached

This paper systematically evaluates component-wise quantization of small vision-language models on Jetson edge devices, finding that model architecture (MoE vs dense) significantly affects quantization sensitivity and that quantization errors are largely additive except along modality-alignment paths.

0 favorites 0 likes
#hardware-aware

Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation

arXiv cs.AI · 2026-07-03 Cached

Hawk is a training-free framework that uses hardware-aware knowledge to improve NPU kernel generation via LLMs, raising generation accuracy from 49.4% to 80.0% and achieving up to 2.2× execution speedup over state-of-the-art baselines.

0 favorites 0 likes
#hardware-aware

Gram Newton-Schulz: A Fast, Hardware-Aware Newton-Schulz Algorithm for Muon

Hacker News Top · 2026-06-09 Cached

This blog post presents Gram Newton-Schulz, a hardware-aware optimization of the Newton-Schulz orthogonalization procedure used in the Muon optimizer, achieving significant speedups for training large language models while preserving model quality.

0 favorites 0 likes
#hardware-aware

AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems

arXiv cs.LG · 2026-05-22 Cached

AutoMCU is a multi-agent system leveraging LLMs to automate neural network design for microcontroller units, significantly reducing customization time while ensuring feasibility under hardware constraints.

0 favorites 0 likes
#hardware-aware

@AYi_AInotes: Fellow developers working on LLM production deployment, check out Andrew Ng's new course. The free version gives you access to all videos and base code. This course is not another rerun of the 'Attention is All You Need' math derivation, nor another set of mystical prompt-tuning tricks, nor yet another toy...

X AI KOLs Timeline · 2026-05-14

Andrew Ng has launched a new course on LLM production deployment. The free version provides access to all videos and base code. The course dives deep into LLM internals, inference optimization (such as quantization, KV Cache, Flash Attention, speculative decoding), and hardware-aware optimization. Taught by AMD's VP of Engineering, it aims to help developers transform Transformer from an academic concept into a debuggable, optimizable engineering tool.

0 favorites 0 likes
← Back to home

Submit Feedback