Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package openvino for openSUSE:Factory checked in at 2025-12-04 11:22:31 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/openvino (Old) and /work/SRC/openSUSE:Factory/.openvino.new.1939 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "openvino" Thu Dec 4 11:22:31 2025 rev:17 rq:1320927 version:2025.4.0 Changes: -------- --- /work/SRC/openSUSE:Factory/openvino/openvino.changes 2025-09-08 09:58:28.104747799 +0200 +++ /work/SRC/openSUSE:Factory/.openvino.new.1939/openvino.changes 2025-12-04 11:27:17.251551908 +0100 @@ -1,0 +2,50 @@ +Tue Dec 2 22:43:52 UTC 2025 - Alessandro de Oliveira Faria <[email protected]> + +- 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. + +------------------------------------------------------------------- @@ -238 +288 @@ - Windows and Linux. + Linux. @@ -293,4 +342,0 @@ - * The OpenVINO Model Server now supports native Windows Server - deployments, allowing developers to leverage better - performance by eliminating container overhead and simplifying - GPU deployment. Old: ---- openvino-2025.3.0.obscpio New: ---- openvino-2025.4.0.obscpio ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ openvino.spec ++++++ --- /var/tmp/diff_new_pack.O5OKMJ/_old 2025-12-04 11:27:21.703740305 +0100 +++ /var/tmp/diff_new_pack.O5OKMJ/_new 2025-12-04 11:27:21.703740305 +0100 @@ -31,13 +31,13 @@ %define pythons python3 %endif %define __builder ninja -%define so_ver 2530 +%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: 2025.3.0 +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 ++++++ _service ++++++ --- /var/tmp/diff_new_pack.O5OKMJ/_old 2025-12-04 11:27:21.747742167 +0100 +++ /var/tmp/diff_new_pack.O5OKMJ/_new 2025-12-04 11:27:21.747742167 +0100 @@ -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">2025.3.0</param> - <param name="version">2025.3.0</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-2025.3.0.obscpio -> openvino-2025.4.0.obscpio ++++++ /work/SRC/openSUSE:Factory/openvino/openvino-2025.3.0.obscpio /work/SRC/openSUSE:Factory/.openvino.new.1939/openvino-2025.4.0.obscpio differ: char 48, line 1 ++++++ openvino.obsinfo ++++++ --- /var/tmp/diff_new_pack.O5OKMJ/_old 2025-12-04 11:27:21.819745214 +0100 +++ /var/tmp/diff_new_pack.O5OKMJ/_new 2025-12-04 11:27:21.823745384 +0100 @@ -1,5 +1,5 @@ name: openvino -version: 2025.3.0 -mtime: 1756212984 -commit: 44526285f241251e9543276572676365fbe542a4 +version: 2025.4.0 +mtime: 1763052589 +commit: 7a975177ff432c687e5619e8fb22e4bf265e48b7
