Seongwoo Choi / Journal

Run your own LLM server with vLLM

From the first request to a monitored server for a whole team: Docker on NVIDIA GPUs, Qwen and Phind-CodeLlama, many users at once, GPU sizing, dashboards and alerts.

Start here: vLLM quickstart: serve a model with an OpenAI-style API

Processors, explained by looking inside

x86, Arm and RISC-V compared by compiling the same code, then the companies behind them.

Start here: One dot product, three instruction sets