Archives

A comprehensive, from-zero guide to GPU hardware buzzwords: HBM, memory bandwidth, FP8/FP4, NVLink, H100 vs H200 vs B200 vs GB200, NVL72 racks, AMD Instinct, TPUs, Groq, Cerebras — plus what to actually run in a homelab and why datacenter GPU infra is genuinely hard.

The complete slide deck covering the production inference optimization strategy: architecture, benchmarks, routing, and cost analysis.

Architectural specification for a production inference optimization strategy for the agentic inference cloud.

Hands-on benchmark of quantization levels on a 1.5B model: decode throughput, TPOT, and memory footprint compared across FP16, Q8_0, and Q4_K_M.

Slide deck on optimizing LLM inference for the agentic era: quantization, KV cache, batching, and bandwidth-bound decoding.

A complete, beginner-friendly guide to vLLM: what inference actually is, how to build vLLM from source on an Apple Silicon Mac with no GPU, every command explained, the three errors I hit and fixed, the flags that matter, and real throughput numbers from my living room.

Cursor picks the right model for you automatically. OpenCode doesn't - yet. Here's a complete, production-shaped guide to adding intelligent auto model selection to OpenCode (or any OpenAI-compatible agent) using vLLM Semantic Router and AgentGateway.

I Almost Built a Grafana Stack—Then AgentGateway Shipped Everything I Needed.

How Cassandra Compression Actually Works (Chunks, Offsets, and Reads)

Giving AgentGateway a Semantic Brain with vLLM Semantic Router - Inside My Homelab

I Traced Personal Agent's Source Code. Inside Was Pi... And It Dreams at 3 AM.

I Built an AI That Decides Which AI to Talk To — Running 24/7 From My Living Room