Related Software

NVIDIA NIM for LLMs fits into a broader inference and platform ecosystem. The following software products are highly relevant when you are deploying, operating, or extending LLM workloads.

Overview

Product	Relation to NIM for LLMs
vLLM	NVIDIA NIM for LLMs packages vLLM as its inference backend, so many request semantics and tuning concepts come directly from vLLM.
NIM Operator	The operator manages NIM deployments by using Kubernetes custom resources and is especially useful for repeatable, production-scale rollouts.
NVIDIA NIM for Vision Language Models	It follows the same NIM operational model, but targets vision-language workloads rather than text-only LLM inference.

Usage Guidance

• Use NVIDIA NIM for LLMs when your workload is text-only and you want a curated, enterprise-ready container for production inference.

• Use vLLM documentation alongside NIM documentation when you need deeper backend-specific context for passthrough arguments or upstream model-serving behavior.

• Use the NIM Operator when your primary deployment target is Kubernetes and you want lifecycle automation around NIM services.

• Use NVIDIA NIM for Vision Language Models when your application must process images and text together instead of text alone.