Tagged with

Gpu

This post thumbnail
Not Every LLM Needs vLLM: A Kubernetes Engineer's Guide to Serving Engines

18 July 2026 07:30 PM

vLLM, SGLang, TGI, Triton, and TensorRT-LLM solve different problems. Here is how to pick the right serving engine for an LLM workload on Kubernetes, with a real engine-swap walkthrough.

This post thumbnail
Your First LLM API on Kubernetes: From Model to Curl Request

24 June 2026 06:30 PM

Deploy Qwen2.5-1.5B-Instruct on a Kubernetes GPU node with vLLM, expose it as an OpenAI-compatible API, and verify it with a real curl request.