SGLang Model-Free NIM is a production-ready inference microservice that serves a broad range of LLMs supplied at runtime in Hugging Face format, with automatic backend selection and optimized configurations.
SGLang Model-Free NIM (Experimental) Container Overview
Description
SGLang Model-Free NIM 2.1.7-variant is a NIM microservice container designed to support a broad range of LLMs. It includes a production-ready inference runtime with optimized inference engines from NVIDIA and the community—such as SGLang. When provided with an LLM at container runtime, stored in a Hugging Face format, the NIM identifies the model’s architecture and quantization, selects the appropriate inference backend, applies preconfigured settings for the model and backend, and begins serving the model for inference. For more information, see the NIM documentation and supported model architectures.
No model weights, checkpoints, or model artifacts are included or distributed with this container.
The container components are ready for commercial or non-commercial use.
License/Terms of Use:
GOVERNING TERMS: The NIM container is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.
Customer-provided models are governed by their applicable license terms and are not provided by NVIDIA as part of this container.
You are responsible for ensuring that your use of customer-provided models complies with all applicable laws and license terms.
Deployment Geography
Global
Release Date
NGC 10/23/2026 (earliest provisional target, revisable or later) via link
Program Classes
This NIM container does not include or automatically distribute model artifacts.
| Model Name & Link | Use Case | How to Pull the Model |
|---|---|---|
| Customer-provided compatible models | Run compatible LLMs with the SGLang Model-Free NIM runtime | Provided by the customer at runtime (Manual) |
Deployment Details
The container exposes OpenAI-compatible inference and health endpoints.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Reference(s)
Container Version(s)
2.1.7-variant
Security Common Vulnerabilities and Exposures (CVEs)
Please review the Security Scanning tab on NGC to view the latest security scan results.
For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.
Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Get Help
Getting started with the NIM
Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM documentation for release documentation, deployment guides and more.
NVIDIA Developer Community Forum
Get access to community knowledge base articles and support cases (NVIDIA Developer Forums).