AI Hardware - SkrewAI

AI Hardware

Groq's LPU Architecture: Why Deterministic Compute Matters for AI

Groq's Language Processing Unit takes a radically different approach to AI inference, replacing GPU parallelism with deterministic compute for predictable, ultra-fast performance.

AMD

AMD's AIE4ML Framework: Compiling Neural Networks for NPUs

AMD researchers unveil AIE4ML, an end-to-end compiler framework that maps neural networks to next-gen AI Engines, achieving significant speedups over CPU implementations for ML workloads.

LLM infrastructure

FPGA-Based CXL Memory Architecture Tackles LLM KV-Cache Bottlenec

New research proposes CXL-SpecKV, a disaggregated FPGA architecture using CXL memory pooling and speculative prefetching to overcome memory bottlenecks in large language model inference at datacenter scale.

AI Hardware

Apple Silicon ML Benchmarks Reveal Local AI Media Power

New benchmarks of Apple's MLX framework demonstrate the growing capability of on-device AI processing, with major implications for local synthetic media generation.