Release Notes

Release 2.1.1

This release contains the following model updates.

vLLM Model-Free NIM

This is an updated release of the vLLM Model-Free NIM, which lets you run any model supported by vLLM without a model-specific container image. For more information, refer to Model-Free NIM.

Qwen3.8-Flash-Next

This is the initial release of Qwen3.8-Flash-Next. For more information on this model, refer to the model card.

Follow the instructions in the Get Started with Qwen3.8-Flash-Next guide to deploy a NIM VLM container with this model.

For GPU support, refer to the support matrix for Qwen3.8-Flash-Next.

For information about past updates and older versions, refer to the previous release notes.