# vLLM

URL: https://donedeploy.com/technologies/vllm/

[!AI · September 7, 2026GPU Nodes on Kubernetes Without Wasting MoneyNode pools, MIG, time-slicing, scale to zero and spot instances: practical ways to keep Kubernetes GPU costs under control for AI workloads.](https://donedeploy.com/gpu-nodes-kubernetes/)[!AI · August 27, 2026vLLM vs Ollama vs TGI: Choosing an Inference ServerHow vLLM, Ollama and Hugging Face TGI differ in throughput, hardware support and operations, and which one fits your workload.](https://donedeploy.com/vllm-ollama-tgi/)

Questions

## vLLM: frequently asked

Can our existing OpenAI client code talk to vLLM?

Yes. vLLM provides an OpenAI-compatible API, so in most cases you change the base URL and model name. Some advanced features differ, so we test your actual calls.

How do we scale vLLM?

Each replica serves one model on one or more GPUs. We scale replicas on Kubernetes based on queue length or latency, and keep warm capacity because loading a model takes time.

Running vLLM, or deciding whether to? Tell us what you have; the first consultation is free.

[Let's talk »](https://donedeploy.com/lets-talk/)