Tag: #neural-engine
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 2 posts
Running LLMs on Apple Silicon: Inside M4/M5 Architecture for AI Inference
A deep technical dive into Apple M4/M5 Unified Memory Architecture and its implications for LLM inference. Covers the Neural Engine, MLX framework, llama.cpp Metal backend, real benchmarks, and an honest comparison with
2026-03-18 · 14 min read #apple-silicon#m5#model-serving#unified-memory#mlxNPU Deep Dive: How Transformer Architecture Runs Directly on Silicon
A complete technical breakdown of how NPUs differ from CPUs and GPUs, how every transformer operation maps to hardware, and why LLM inference is memory-bound — not compute-bound. From Apple ANE to Qualcomm Hexagon, Groq
2026-03-18 · 22 min read #npu#transformer#ai-hardware#quantization#kv-cache