_service

@@ -2,8 +2,8 @@
   <service name="obs_scm" mode="manual">
     <param name="url">https://github.com/openvinotoolkit/openvino.git</param>
     <param name="scm">git</param>
-    <param name="revision">2025.2.0</param>
-    <param name="version">2025.2.0</param>
+    <param name="revision">2025.4.0</param>
+    <param name="version">2025.4.0</param>
     <param name="submodules">enable</param>
     <param name="filename">openvino</param>
     <param name="exclude">.git</param>

openvino-2025.2.0.obscpio

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c75c27293662056f9098ecf9b0dfbeacf948983df5807a63610313678024adf
-size 743258127

openvino-2025.4.0.obscpio

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deda1db3ae8e8acb506d8937ff4709332bfa0380de14393c6f030b88dd2fc5c4
+size 753350671

openvino.changes

@@ -1,3 +1,102 @@
+-------------------------------------------------------------------
+Tue Dec  2 22:43:52 UTC 2025 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
+
+- Update to 2025.4.0
+- More GenAI coverage and framework integrations to minimize code
+  changes
+  * New models supported:
+    + On CPUs & GPUs: Qwen3-Embedding-0.6B, Qwen3-Reranker-0.6B, 
+      Mistral-Small-24B-Instruct-2501.
+    + On NPUs: Gemma-3-4b-it and Qwen2.5-VL-3B-Instruct.
+  * Preview: Mixture of Experts (MoE) models optimized for CPUs 
+    and GPUs, validated for Qwen3-30B-A3B.
+  * GenAI pipeline integrations: Qwen3-Embedding-0.6B and 
+    Qwen3-Reranker-0.6B for enhanced retrieval/ranking, and 
+    Qwen2.5VL-7B for video pipeline.
+- Broader LLM model support and more model compression 
+  techniques
+  * The Neural Network Compression Framework (NNCF) ONNX backend 
+    now supports INT8 static post-training quantization (PTQ) 
+    and INT8/INT4 weight-only compression to ensure accuracy 
+    parity with OpenVINO IR format models. SmoothQuant algorithm 
+    support added for INT8 quantization.
+  * Accelerated multi-token generation for GenAI, leveraging 
+    optimized GPU kernels to deliver faster inference, smarter 
+    KV-cache reuse, and scalable LLM performance.
+  * GPU plugin updates include improved performance with prefix 
+    caching for chat history scenarios and enhanced LLM accuracy 
+    with dynamic quantization support for INT8.
+- More portability and performance to run AI at the edge, in the 
+  cloud, or locally.
+  * Announcing support for Intel® Core Ultra Processor Series 3.
+  * Encrypted blob format support added for secure model 
+    deployment with OpenVINO GenAI. Model weights and artifacts
+    are stored and transmitted in an encrypted format, reducing
+    risks of IP theft during deployment. Developers can deploy 
+    with minimal code changes using OpenVINO GenAI pipelines.
+  * OpenVINO™ Model Server and OpenVINO™ GenAI now extend 
+    support for Agentic AI scenarios with new features such as
+    output parsing and improved chat templates for reliable 
+    multi-turn interactions, and preview functionality for the 
+    Qwen3-30B-A3B model. OVMS also introduces a preview for 
+    audio endpoints.
+  * NPU deployment is simplified with batch support, enabling 
+    seamless model execution across Intel® Core Ultra 
+    processors while eliminating driver dependencies. Models 
+    are reshaped to batch_size=1 before compilation.
+  * The improved NVIDIA Triton Server* integration with 
+    OpenVINO backend now enables developers to utilize Intel
+    GPUs or NPUs for deployment.
+
+-------------------------------------------------------------------
+Sun Sep  7 01:21:19 UTC 2025 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
+
+- Update to 2025.3.0
+- More GenAI coverage and framework integrations to minimize code
+  changes
+  * New models supported: Phi-4-mini-reasoning, AFM-4.5B, 
+    Gemma-3-1B-it, Gemma-3-4B-it, and Gemma-3-12B,
+  * NPU support added for: Qwen3-1.7B, Qwen3-4B, and Qwen3-8B.
+  * LLMs optimized for NPU now available on OpenVINO Hugging
+    Face collection.
+- Broader LLM model support and more model compression techniques
+  * The NPU plug-in adds support for longer contexts of up to 
+    8K tokens, dynamic prompts, and dynamic LoRA for improved 
+    LLM performance.
+  * The NPU plug-in now supports dynamic batch sizes by reshaping
+    the model to a batch size of 1 and concurrently managing
+    multiple inference requests, enhancing performance and
+    optimizing memory utilization.
+  * Accuracy improvements for GenAI models on both built-in 
+    and discrete graphics achieved through the implementation 
+    of the key cache compression per channel technique, in 
+    addition to the existing KV cache per-token compression
+    method.
+  * OpenVINO™ GenAI introduces TextRerankPipeline for improved
+    retrieval relevance and RAG pipeline accuracy, plus 
+    Structured Output for enhanced response reliability and 
+    function calling while ensuring adherence to predefined
+    formats.
+- More portability and performance to run AI at the edge,
+  in the cloud, or locally.
+  * Announcing support for Intel® Arc™ Pro B-Series 
+    (B50 and B60).
+  * Preview: Hugging Face models that are GGUF-enabled for 
+    OpenVINO GenAI are now supported by the OpenVINO™ Model
+    Server for popular LLM model architectures such as 
+    DeepSeek Distill, Qwen2, Qwen2.5, and Llama 3. 
+    This functionality reduces memory footprint and 
+    simplifies integration for GenAI workloads.
+  * With improved reliability and tool call accuracy, 
+    the OpenVINO™ Model Server boosts support for 
+    agentic AI use cases on AI PCs, while enhancing 
+    performance on Intel CPUs, built-in GPUs, and NPUs.
+  * int4 data-aware weights compression, now supported in the
+    Neural Network Compression Framework (NNCF) for ONNX 
+    models, reduces memory footprint while maintaining 
+    accuracy and enables efficient deployment in 
+    resource-constrained environments.
+
 -------------------------------------------------------------------
 Wed Jun 25 01:09:14 UTC 2025 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
 
@@ -186,7 +285,7 @@ Mon Apr 14 06:52:03 UTC 2025 - Alessandro de Oliveira Faria <cabelo@opensuse.org
   cloud, or locally.
   * Additional LLM performance optimizations on Intel® Core™ Ultra
     200H series processors for improved 2nd token latency on
-    Windows and Linux.
+    Linux.
   * Enhanced performance and efficient resource utilization with
     the implementation of Paged Attention and Continuous Batching
     by default in the GPU plugin.
@@ -241,10 +340,6 @@ Sun Feb  9 03:36:41 UTC 2025 - Alessandro de Oliveira Faria <cabelo@opensuse.org
     directly within Keras 3 workflows for faster AI inference on
     CPUs, built-in GPUs, discrete GPUs, and NPUs. This feature is
     available with the latest Keras 3.8 release.
-  * The OpenVINO Model Server now supports native Windows Server
-    deployments, allowing developers to leverage better
-    performance by eliminating container overhead and simplifying
-    GPU deployment.
 - Support Change and Deprecation Notices
   * Now deprecated:
     + Legacy prefixes l_, w_, and m_ have been removed from

openvino.obsinfo

@@ -1,4 +1,4 @@
 name: openvino
-version: 2025.2.0
-mtime: 1749227913
-commit: c01cd93e24d1cd78bfbb401eed51c08fb93e0816
+version: 2025.4.0
+mtime: 1763052589
+commit: 7a975177ff432c687e5619e8fb22e4bf265e48b7

openvino.spec

@@ -31,13 +31,13 @@
 %define pythons python3
 %endif
 %define __builder ninja
-%define so_ver 2520
+%define so_ver 2540
 %define shlib lib%{name}%{so_ver}
 %define shlib_c lib%{name}_c%{so_ver}
 %define prj_name OpenVINO
 
 Name:           openvino
-Version:        2025.2.0
+Version:        2025.4.0
 Release:        0
 Summary:        A toolkit for optimizing and deploying AI inference
 # Let's be safe and put all third party licenses here, no matter that we use specific thirdparty libs or not