Hi HN,

I’m Padam, a developer in Dubai.

Over the last 2 years I’ve been experimenting with running LLM inference without GPUs.

AlifZetta is a prototype AI-native OS that virtualizes GPU-style parallelism from CPU SIMD.

Key details: • ~67k lines of Rust • kernel-level scheduling • quantized inference • 6 AI models

Curious what the HN community thinks.