Tag: #unified-memory
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 2 posts
MLX Deep Dive — Apple's ML Framework for Apple Silicon: Unified Memory, Lazy Graphs, and the Mac-Native Flow (2026 Hands-On)
MLX is the array framework that Apple's ML team — the same people who previously built PyTorch and JAX — rewrote from scratch for Apple Silicon. The core thesis is one sentence: the M-series GPU shares RAM with the CPU,
2026-05-14 · 19 min read #mlx#apple-silicon#ml-framework#unified-memory#metalRunning 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#mlx