Snack On AI

Never miss a post subscribe below to get the latest updates and exclusive content delivered straight to your inbox.

Apr 14, 2026

Unsloth: Fine-Tuning Is Not Slow. Your Kernels Are.

Your Kernels Are Slow. Here's What Unsloth Did About It.

Apr 12, 2026

vLLM: The Inference Engine You Think You Understand But Probably Don't

How UC Berkeley Stole 50 Years of OS Research and Made LLM Serving 24x Faster

Apr 11, 2026

AIBrix: The New Frontier of Cloud-Native LLM Orchestration

The missing orchestration layer that makes vLLM production-ready at scale

Apr 10, 2026

Nebula-S, SVMS1-4B, and the On-Device Reasoning Architecture Nobody Is Talking About Correctly

Everyone is arguing about which 70B model wins on MMLU. Meanwhile, a small team in Austin is quietly stacking a multi-stream reasoning architecture on top of Qwen3-4B and claiming it beats models twice its size on edge hardware. Let's crack it open.

Apr 9, 2026

TensorRT-LLM: NVIDIA's Inference Compiler Is Not What You Think It Is

The inference compiler NVIDIA doesn't want you to call a compiler

Apr 8, 2026

The Ralph Loop: Why a Bash While Loop Is One of the Most Honest Architectures in Agentic AI

A PRD-driven, test-gated, self-correcting autonomous coding loop built on Claude Code. Deceptively simple. Surprisingly powerful. And the industry's best-kept design pattern hiding in plain sight.