[DOCS] Rel branch refs

docs/source/dev_guide/advanced_install/advanced_install_guide_compilation.md

@@ -150,7 +150,7 @@ packages:
 
 ### (Optional) Step 6: Install OpenVINO™ GenAI (only for Ubuntu)
 
-To use [gvagenai element](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/dlstreamer/elements/gvagenai.html)
+To use [gvagenai element](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/elements/gvagenai.html)
 you need to install the [OpenVINO GenAI archive](https://docs.openvino.ai/2026/get-started/install-openvino/install-openvino-genai.html) package.
 
 <!--hide_directive::::{tab-set}

docs/source/dev_guide/custom_processing.md

@@ -129,7 +129,6 @@ to the
 
 **Current Support Limitations**
 
-
 At this time, only **detection** and **classification** tasks are supported:
 
 - **Object Detection** (`GstAnalyticsODMtd`) - works only with the

docs/source/dev_guide/gpu_device_selection.md

@@ -9,7 +9,7 @@ This article describes how to select a GPU device on a multi-GPU system.
 In case of video decoding running on CPU and inference running on GPU, the
 `device` property in inference elements enables you to select the GPU device
 according to the
-[OpenVINO™ GPU device naming convention](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/gpu-device.html#device-naming-convention)
+[OpenVINO™ GPU device naming convention](https://docs.openvino.ai/2026/openvino-workflow/running-inference/inference-devices-and-modes/gpu-device.html#device-naming-convention)
 , with devices enumerated as **GPU.0**, **GPU.1**, etc., for example:
 
 ```bash

docs/source/dev_guide/lvms.md

@@ -2,7 +2,7 @@
 
 This article explains how to prepare models based on the [Hugging Face](https://huggingface.co/welcome) [`transformers`](https://github.com/huggingface/transformers) library for integration with the Deep Learning Streamer pipeline.
 
-Many transformer-based models can be converted to OpenVINO™ IR format using [optimum-cli](https://huggingface.co/docs/optimum-intel/en/openvino/export). DL Streamer supports selected Hugging Face architectures for tasks such as image classification, object detection, audio transcription, and more. See the [Supported Models](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/dlstreamer/supported_models.html) table for details.
+Many transformer-based models can be converted to OpenVINO™ IR format using [optimum-cli](https://huggingface.co/docs/optimum-intel/en/openvino/export). DL Streamer supports selected Hugging Face architectures for tasks such as image classification, object detection, audio transcription, and more. See the [Supported Models](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/supported_models.html) table for details.
 
 > **NOTE:** The instructions below are comprehensive, but for convenience, we recommend using the
 > [download_hf_models.py](https://github.com/open-edge-platform/dlstreamer/blob/main/scripts/download_models/download_hf_models.py)
@@ -12,7 +12,7 @@ Many transformer-based models can be converted to OpenVINO™ IR format using [o
 
 ## Optimum-Intel Supported Models
 
-The list available [here](https://huggingface.co/docs/optimum-intel/en/openvino/models) includes models that can be converted to IR format with a single `optimum-cli` command. If a model architecture is [supported by DL Streamer](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/dlstreamer/supported_models.html#supported-architectures), it can typically be prepared as follows:
+The list available [here](https://huggingface.co/docs/optimum-intel/en/openvino/models) includes models that can be converted to IR format with a single `optimum-cli` command. If a model architecture is [supported by DL Streamer](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/supported_models.html#supported-architectures), it can typically be prepared as follows:
 
 ```bash
 optimum-cli export openvino --model provider_id/model_id --weight-format=int8 output_path

docs/source/dev_guide/model_preparation.md

@@ -43,7 +43,7 @@ You can either:
    [Open Model Zoo](https://github.com/openvinotoolkit/open_model_zoo)
    (already in the IR format).
 2. Use
-   [OpenVINO™ Toolkit Model Conversion](https://docs.openvino.ai/2024/openvino-workflow/model-preparation/convert-model-to-ir.html)
+   [OpenVINO™ Toolkit Model Conversion](https://docs.openvino.ai/2026/openvino-workflow/model-preparation/convert-model-to-ir.html)
    method for converting your model from the training framework format
    (e.g., TensorFlow) to the IR format.
 
@@ -52,7 +52,7 @@ When using a pre-trained model from Open Model Zoo, consider using the
 tool to facilitate the model downloading process.
 
 When converting a custom model, you can optionally utilize the
-[Post-Training Model Optimization and Compression](https://docs.openvino.ai/2024/openvino-workflow/model-optimization.html)
+[Post-Training Model Optimization and Compression](https://docs.openvino.ai/2026/openvino-workflow/model-optimization.html)
 for converting the model into a performance efficient, and more
 hardware-friendly representation. For example you can quantize it from 32-bit
 floating point-precision into 8-bit integer precision. This gives a

docs/source/dev_guide/openvino_custom_operations.md

@@ -22,7 +22,7 @@ Before using custom operations, you need:
 1. **OpenVINO™ Extension Library** - A compiled `.so` file (on Linux) containing the implementation of custom operations
 2. **Model with Custom Operations** - An OpenVINO™ IR model that uses the custom operations defined in the extension library
 
-For information on creating OpenVINO™ extension libraries, refer to the [OpenVINO™ Extensibility documentation](https://docs.openvino.ai/2025/documentation/openvino-extensibility.html).
+For information on creating OpenVINO™ extension libraries, refer to the [OpenVINO™ Extensibility documentation](https://docs.openvino.ai/2026/documentation/openvino-extensibility.html).
 
 ## Usage
 

docs/source/dev_guide/python_bindings.md

@@ -70,7 +70,7 @@ The *gvapython* element is implemented in "C" language as a normal GStreamer
 element and it invokes Python functions via "C" interface (Python.h).
 
 See the samples for the *gvapython* element in
-[face_detection_and_classification](https://github.com/dlstreamer/dlstreamer/tree/main/samples/gstreamer/gst_launch/gvapython/face_detection_and_classification) folder.
+[face_detection_and_classification](https://github.com/open-edge-platform/dlstreamer/tree/main/samples/gstreamer/gst_launch/gvapython/face_detection_and_classification) folder.
 
 ## 4. Performance considerations
 

docs/source/dev_guide/yolo_models.md

@@ -5,7 +5,7 @@ integration with the Deep Learning Streamer pipeline.
 
 ## Ultralytics Model Preparation
 
-All models supported by the [ultralytics/ultralytics](https://github.com/ultralytics/ultralytics) library can be converted to OpenVINO™ IR format by using the [Ultralytics exporter](https://docs.ultralytics.com/integrations/openvino/). DL Streamer supports many Ultralytics YOLO architectures for tasks such as zero-shot object detection, oriented object detection, segmentation, pose estimation, and more. See the [Supported Models](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/dlstreamer/supported_models.html) table for details.
+All models supported by the [ultralytics/ultralytics](https://github.com/ultralytics/ultralytics) library can be converted to OpenVINO™ IR format by using the [Ultralytics exporter](https://docs.ultralytics.com/integrations/openvino/). DL Streamer supports many Ultralytics YOLO architectures for tasks such as zero-shot object detection, oriented object detection, segmentation, pose estimation, and more. See the [Supported Models](https://docs.openedgeplatform.intel.com/2026.0/edge-ai-libraries/dlstreamer/supported_models.html) table for details.
 
 > **NOTE:** The instructions below are comprehensive, but for convenience, we recommend using the
 > [download_ultralytics_models.py](https://github.com/open-edge-platform/dlstreamer/blob/main/scripts/download_models/download_ultralytics_models.py)

docs/source/get_started/tutorial.md

@@ -217,7 +217,7 @@ Ubuntu.
     If you want to use your own models, you first need to convert them
     to the IR (Intermediate Representation) format. For detailed
     instructions on how to convert models, look
-    [here](https://docs.openvino.ai/2025/openvino-workflow/model-preparation/convert-model-to-ir.html)
+    [here](https://docs.openvino.ai/2026/openvino-workflow/model-preparation/convert-model-to-ir.html)
 
 4.  Export the example video file path:
 
@@ -333,7 +333,7 @@ Follow these steps if you chose Option #2 (Docker) in Install Guide Ubuntu.
 
     If you want to use your own models, first you need to convert them
     in the IR (Intermediate Representation) format. For detailed
-    instructions on how to convert models, look [here](https://docs.openvino.ai/2025/openvino-workflow/model-preparation/convert-model-to-ir.html).
+    instructions on how to convert models, look [here](https://docs.openvino.ai/2026/openvino-workflow/model-preparation/convert-model-to-ir.html).
 
 6.  In the container, export the example video file path:
 

docs/source/index.md

@@ -21,7 +21,7 @@ or at the Edge. DL Streamer consists of:
   for designing, creating, building, and running media analytics
   pipelines. It includes C++ and Python APIs.
 - [Deep Learning Streamer Pipeline
-  Server](https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/dlstreamer-pipeline-server)
+  Server](https://github.com/open-edge-platform/edge-ai-libraries/tree/release-2026.0.0/microservices/dlstreamer-pipeline-server)
   for deploying and scaling media analytics pipelines as
   micro-services on one or many compute nodes. It includes REST APIs
   for pipelines management.
@@ -82,7 +82,7 @@ deploy, and benchmark. They require:
 **DL Streamer** uses OpenVINO™ Runtime inference back-end,
 optimized for Intel hardware platforms and supports over
 [70 NN Intel and open-source community pre-trained models](https://github.com/open-edge-platform/dlstreamer/blob/main/docs/scripts/supported_models.json), and models converted
-[from other training frameworks](https://docs.openvino.ai/2024/openvino-workflow/model-preparation/convert-model-to-ir.html).
+[from other training frameworks](https://docs.openvino.ai/2026/openvino-workflow/model-preparation/convert-model-to-ir.html).
 These models include object detection, object classification, human pose
 detection, sound classification, semantic segmentation, and other use
 cases: SSD, MobileNet, YOLO, Tiny YOLO, EfficientDet, ResNet,
@@ -92,7 +92,7 @@ FasterRCNN, and other models.
 reference apps for the most common media analytics use cases. They are
 included in
 [Deep Learning Streamer Pipeline Framework](https://github.com/open-edge-platform/dlstreamer/tree/main),
-[Deep Learning Streamer Pipeline Server](https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/dlstreamer-pipeline-server),
+[Deep Learning Streamer Pipeline Server](https://github.com/open-edge-platform/edge-ai-libraries/tree/release-2026.0.0/microservices/dlstreamer-pipeline-server),
 [Open Visual Cloud](https://github.com/OpenVisualCloud), and
 [Intel® Edge Software Hub](https://www.intel.com/content/www/us/en/edge-computing/edge-software-hub.html)
 The samples demonstrate C++ and/or Python based: Action Recognition, Face Detection and