> This page is for version Dev.
> For other versions, use one of these documentation indexes:
> - 3.3.0 (default): https://docs.nvidia.com/vss/3.3.0/llms.txt
> - Dev: https://docs.nvidia.com/vss/dev/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/vss/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/vss/_mcp/server.

# VSS 2.X Release Notes

## VSS 2.4.1

These are the VSS 2.4.1 Release Notes.

### Key Features and Enhancements

* Support for [NVIDIA Cosmos-Reason2](https://huggingface.co/nvidia/Cosmos-Reason2-8B) VLM
* Support for  Qwen3-VL models including [Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct) and [Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) VLM
* Support for GH200 and GB200 platforms.
* Removed support for VILA-1.5 and NVILA models.

## VSS 2.4.0

These are the VSS 2.4.0 Release Notes.

### Key Features and Enhancements

* Support for [NVIDIA Cosmos-Reason1](https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/models/cosmos-reason1-7b) VLM

* Two new APIs

  * `/generate_vlm_captions` to generate VLM captions for a video without summarization.
  * `/reviewAlert` to review an externally generated alert using VLM.

* New reference deployment, Event Reviewer, to demonstrate review of an externally generated alert using a VLM.

* VSS accuracy evaluation framework to evaluate accuracy on your own videos.

* New parameters in the `/summarize` API:

  * `system_prompt` - System prompt for the VLM.

* New retrieval strategies for CA-RAG.

## VSS 2.3.1

These are the VSS 2.3.1 Release Notes.

### Key Features and Enhancements

* Support for NVIDIA Blackwell B200 GPU
* OneClick script support for GCP deployments
* Performance improvements for file burst mode

## VSS 2.3.0

These are the VSS 2.3.0 Release Notes.

### Key Features and Enhancements

* Support for Audio in Summarization and Q\&A
* Support for preprocessing a video to generate Set of Marks (SOM) prompting and additional CV metadata for better accuracy
* Gradio UI Improvements
* Additional runtime parameters that can be configured through the `/summarize` API

| Parameter                                                                   | Description                                             |
| --------------------------------------------------------------------------- | ------------------------------------------------------- |
| `summarize_top_p`, `summarize_temperature`, `summarize_max_tokens`          | LLM sampling parameters for summarization.              |
| `chat_top_p`, `chat_temperature`, `chat_max_tokens`                         | LLM sampling parameters for Q\&A.                       |
| `notification_top_p`, `notification_temperature`, `notification_max_tokens` | LLM sampling parameters for alerts and event detection. |

* New API `/alerts/recent` to get recent alerts for all live streams.
* Stability improvements
* Single GPU Deployment

## VSS 2.2.0

These are the VSS 2.2.0 Release Notes.
This release is an Engineering Release to introduce some of the new features.
This release includes several fixes from the previous VSS releases and additional changes.

### Key Features and Enhancements

* Enhanced multi-stream / concurrent mode support
* GraphRAG performance improvements.
* Support for [NVILA research model](https://huggingface.co/Efficient-Large-Model/NVILA-15B).
* Additional runtime parameters that can be configured through the `/summarize` API

| Parameter                             | Description                                                           |
| ------------------------------------- | --------------------------------------------------------------------- |
| `vlm_input_width`, `vlm_input_height` | Configure the input resolution of the frames to the VLM.              |
| `num_frames_per_chunk`                | Configure the number of frames to sample from each chunk.             |
| `summarize_batch_size`                | LLM batch size for summarization.                                     |
| `rag_top_k`                           | Number of top rerank results to use during Q\&A.                      |
| `rag_batch_size`                      | Number of VLM captions to be batched together for creating the graph. |