pool/openvino
SHA256
12
0
Fork 1
Code Issues Pull Requests Activity

- Temporarily inserted gcc-13 in Tumbleweed/Factory/Slowroll:

Browse Source 
Because there is an incompatibility of the source code of the 
  level-zero library and npu module with gcc-14. I am working 
  with Intel on tests to return to native gcc.
- Update to 2024.4.0
- Summary of major features and improvements  
  * More Gen AI coverage and framework integrations to minimize
    code changes
    + Support for GLM-4-9B Chat, MiniCPM-1B, Llama 3 and 3.1,
      Phi-3-Mini, Phi-3-Medium and YOLOX-s models.
    + Noteworthy notebooks added: Florence-2, NuExtract-tiny
      Structure Extraction, Flux.1 Image Generation, PixArt-α:
      Photorealistic Text-to-Image Synthesis, and Phi-3-Vision
      Visual Language Assistant.
  * Broader Large Language Model (LLM) support and more model
    compression techniques.
    + OpenVINO™ runtime optimized for Intel® Xe Matrix Extensions
      (Intel® XMX) systolic arrays on built-in GPUs for efficient
      matrix multiplication resulting in significant LLM
      performance boost with improved 1st and 2nd token
      latency, as well as a smaller memory footprint on
      Intel® Core™ Ultra Processors (Series 2).
    + Memory sharing enabled for NPUs on Intel® Core™ Ultra
      Processors (Series 2) for efficient pipeline integration
      without memory copy overhead.
    + Addition of the PagedAttention feature for discrete GPUs*
      enables a significant boost in throughput for parallel
      inferencing when serving LLMs on Intel® Arc™ Graphics
      or Intel® Data Center GPU Flex Series.
  * More portability and performance to run AI at the edge,
    in the cloud, or locally.
    + OpenVINO™ Model Server now comes with production-quality
      support for OpenAI-compatible API which enables i
      significantly higher throughput for parallel inferencing
      on Intel® Xeon® processors when serving LLMs to many
      concurrent users.
    + Improved performance and memory consumption with prefix
      caching, KV cache compression, and other optimizations
      for serving LLMs using OpenVINO™ Model Server.
    + Support for Python 3.12.
- Support Change and Deprecation Notices
  * Using deprecated features and components is not advised.
    They are available to enable a smooth transition to new
    solutions and will be discontinued in the future.
    To keep using discontinued features, you will have to
    revert to the last LTS OpenVINO version supporting them.
    For more details, refer to the OpenVINO Legacy Features
    and Components page.
  * Discontinued in 2024.0:
    + Runtime components:
      - Intel® Gaussian & Neural Accelerator (Intel® GNA).
        Consider using the Neural Processing Unit (NPU) for
        low-powered systems like Intel® Core™ Ultra or
        14th generation and beyond.
      - OpenVINO C++/C/Python 1.0 APIs (see 2023.3 API
        transition guide for reference).
      - All ONNX Frontend legacy API (known as
        ONNX_IMPORTER_API)
      -'PerfomanceMode.UNDEFINED' property as part of the
        OpenVINO Python API
    + Tools:
       - Deployment Manager. See installation and deployment
         guides for current distribution options.
       - Accuracy Checker.
       - Post-Training Optimization Tool (POT). Neural Network
         Compression Framework (NNCF) should be used instead.
       - A Git patch for NNCF integration with huggingface/
         transformers. The recommended approach is to use
         huggingface/optimum-intel for applying NNCF
         optimization on top of models from Hugging Face.
       - Support for Apache MXNet, Caffe, and Kaldi model
         formats. Conversion to ONNX may be used as a
         solution.
  * Deprecated and to be removed in the future:
    + The macOS x86_64 debug bins will no longer be
      provided with the OpenVINO toolkit, starting with
      OpenVINO 2024.5.
    + Python 3.8 is now considered deprecated, and it will not
      be available beyond the 2024.4 OpenVINO version.
    + dKMB support is now considered deprecated and will be
      fully removed with OpenVINO 2024.5
    + Intel® Streaming SIMD Extensions (Intel® SSE) will be
      supported in source code form, but not enabled in the
      binary package by default, starting with OpenVINO 2025.0
    + The openvino-nightly PyPI module will soon be discontinued.
      End-users should proceed with the Simple PyPI nightly repo
      instead. More information in Release Policy.
    + The OpenVINO™ Development Tools package (pip install
      openvino-dev) will be removed from installation options and
      distribution channels beginning with OpenVINO 2025.0.
    + Model Optimizer will be discontinued with OpenVINO 2025.0.
      Consider using the new conversion methods instead. For more
      details, see the model conversion transition guide.
    + OpenVINO property Affinity API will be discontinued with
      OpenVINO 2025.0. It will be replaced with CPU binding
      configurations (ov::hint::enable_cpu_pinning).
    + OpenVINO Model Server components:
      - “auto shape” and “auto batch size” (reshaping a model in
      runtime) will be removed in the future. OpenVINO’s dynamic
      shape models are recommended instead.
    + A number of notebooks have been deprecated. For an
      up-to-date listing of available notebooks, refer to the
      OpenVINO™ Notebook index (openvinotoolkit.github.io).

OBS-URL: https://build.opensuse.org/package/show/science:machinelearning/openvino?expand=0&rev=19
This commit is contained in:
Guillaume GARDET
2024-10-17 06:21:51 +00:00
committed by Git OBS Bridge
parent 22e8eb5619
commit fd89371cd6
6 changed files with 117 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
_service
View File

@@ -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">2024.3.0</param>
<param name="version">2024.3.0</param>
<param name="revision">2024.4.0</param>
<param name="version">2024.4.0</param>
<param name="submodules">enable</param>
<param name="filename">openvino</param>
<param name="exclude">.git</param>

3
openvino-2024.3.0.obscpio
View File

@@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bacc2b9540afda6c5bd6d17ddea35afe17caefdd4fa1a350ed1c8be2eb290981
size 1055294991

3
openvino-2024.4.0.obscpio Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fde6d7a29c8284b72866b02b37f6eaff9143f4a3b05f48a098d4965cc53c9248
size 1102958095

107
openvino.changes
View File

@@ -1,3 +1,110 @@
-------------------------------------------------------------------
Tue Oct 15 00:56:54 UTC 2024 - Alessandro de Oliveira Faria <cabelo@opensuse.org>
- Temporarily inserted gcc-13 in Tumbleweed/Factory/Slowroll:
Because there is an incompatibility of the source code of the
level-zero library and npu module with gcc-14. I am working
with Intel on tests to return to native gcc.
- Update to 2024.4.0
- Summary of major features and improvements  
* More Gen AI coverage and framework integrations to minimize
code changes
+ Support for GLM-4-9B Chat, MiniCPM-1B, Llama 3 and 3.1,
Phi-3-Mini, Phi-3-Medium and YOLOX-s models.
+ Noteworthy notebooks added: Florence-2, NuExtract-tiny
Structure Extraction, Flux.1 Image Generation, PixArt-α:
Photorealistic Text-to-Image Synthesis, and Phi-3-Vision
Visual Language Assistant.
* Broader Large Language Model (LLM) support and more model
compression techniques.
+ OpenVINO™ runtime optimized for Intel® Xe Matrix Extensions
(Intel® XMX) systolic arrays on built-in GPUs for efficient
matrix multiplication resulting in significant LLM
performance boost with improved 1st and 2nd token
latency, as well as a smaller memory footprint on
Intel® Core™ Ultra Processors (Series 2).
+ Memory sharing enabled for NPUs on Intel® Core™ Ultra
Processors (Series 2) for efficient pipeline integration
without memory copy overhead.
+ Addition of the PagedAttention feature for discrete GPUs*
enables a significant boost in throughput for parallel
inferencing when serving LLMs on Intel® Arc™ Graphics
or Intel® Data Center GPU Flex Series.
* More portability and performance to run AI at the edge,
in the cloud, or locally.
+ OpenVINO™ Model Server now comes with production-quality
support for OpenAI-compatible API which enables i
significantly higher throughput for parallel inferencing
on Intel® Xeon® processors when serving LLMs to many
concurrent users.
+ Improved performance and memory consumption with prefix
caching, KV cache compression, and other optimizations
for serving LLMs using OpenVINO™ Model Server.
+ Support for Python 3.12.
- Support Change and Deprecation Notices
* Using deprecated features and components is not advised.
They are available to enable a smooth transition to new
solutions and will be discontinued in the future.
To keep using discontinued features, you will have to
revert to the last LTS OpenVINO version supporting them.
For more details, refer to the OpenVINO Legacy Features
and Components page.
* Discontinued in 2024.0:
+ Runtime components:
- Intel® Gaussian & Neural Accelerator (Intel® GNA).
Consider using the Neural Processing Unit (NPU) for
low-powered systems like Intel® Core™ Ultra or
14th generation and beyond.
- OpenVINO C++/C/Python 1.0 APIs (see 2023.3 API
transition guide for reference).
- All ONNX Frontend legacy API (known as
ONNX_IMPORTER_API)
-'PerfomanceMode.UNDEFINED' property as part of the
OpenVINO Python API
+ Tools:
- Deployment Manager. See installation and deployment
guides for current distribution options.
- Accuracy Checker.
- Post-Training Optimization Tool (POT). Neural Network
Compression Framework (NNCF) should be used instead.
- A Git patch for NNCF integration with huggingface/
transformers. The recommended approach is to use
huggingface/optimum-intel for applying NNCF
optimization on top of models from Hugging Face.
- Support for Apache MXNet, Caffe, and Kaldi model
formats. Conversion to ONNX may be used as a
solution.
* Deprecated and to be removed in the future:
+ The macOS x86_64 debug bins will no longer be
provided with the OpenVINO toolkit, starting with
OpenVINO 2024.5.
+ Python 3.8 is now considered deprecated, and it will not
be available beyond the 2024.4 OpenVINO version.
+ dKMB support is now considered deprecated and will be
fully removed with OpenVINO 2024.5
+ Intel® Streaming SIMD Extensions (Intel® SSE) will be
supported in source code form, but not enabled in the
binary package by default, starting with OpenVINO 2025.0
+ The openvino-nightly PyPI module will soon be discontinued.
End-users should proceed with the Simple PyPI nightly repo
instead. More information in Release Policy.
+ The OpenVINO™ Development Tools package (pip install
openvino-dev) will be removed from installation options and
distribution channels beginning with OpenVINO 2025.0.
+ Model Optimizer will be discontinued with OpenVINO 2025.0.
Consider using the new conversion methods instead. For more
details, see the model conversion transition guide.
+ OpenVINO property Affinity API will be discontinued with
OpenVINO 2025.0. It will be replaced with CPU binding
configurations (ov::hint::enable_cpu_pinning).
+ OpenVINO Model Server components:
- “auto shape” and “auto batch size” (reshaping a model in
runtime) will be removed in the future. OpenVINO’s dynamic
shape models are recommended instead.
+ A number of notebooks have been deprecated. For an
up-to-date listing of available notebooks, refer to the
OpenVINO™ Notebook index (openvinotoolkit.github.io).
-------------------------------------------------------------------
Wed Oct 2 20:56:59 UTC 2024 - Giacomo Comes <gcomes.obs@gmail.com>

6
openvino.obsinfo
View File

@@ -1,4 +1,4 @@
name: openvino
version: 2024.3.0
mtime: 1721394417
commit: 1e3b88e4e3f89774923e04e845428579f8ffa0fe
version: 2024.4.0
mtime: 1725541792
commit: c3152d32c9c7df71397e5a3aba1d935c49eec598

12
openvino.spec
View File

@@ -31,13 +31,13 @@
%define pythons python3
%endif
%define __builder ninja
%define so_ver 2430
%define so_ver 2440
%define shlib lib%{name}%{so_ver}
%define shlib_c lib%{name}_c%{so_ver}
%define prj_name OpenVINO
Name: openvino
Version: 2024.3.0
Version: 2024.4.0
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
@@ -59,11 +59,7 @@ Patch5: openvino-remove-npu-compile-tool.patch
BuildRequires: ade-devel
BuildRequires: cmake
BuildRequires: fdupes
%if %{defined isLeap15}
BuildRequires: gcc13-c++
%else
BuildRequires: gcc-c++
%endif
BuildRequires: ninja
BuildRequires: opencl-cpp-headers
# FIXME: /usr/include/onnx/onnx-ml.pb.h:17:2: error: This file was generated by
@@ -285,9 +281,7 @@ This package provides some samples for use with openVINO.
%autosetup -p1
%build
%if %{defined isLeap15}
export CC=gcc-13 CXX=g++-13
%endif
# Otherwise intel_cpu plugin declares an executable stack
%ifarch %{x86_64}
%define build_ldflags -Wl,-z,noexecstack
@@ -331,8 +325,6 @@ export WHEEL_VERSION=%{version} \
%install
%cmake_install
rm %{buildroot}%{_datadir}/%{prj_name}/samples/cpp/thirdparty/nlohmann_json/.cirrus.yml
# Hash-bangs in non-exec python sample scripts
sed -Ei "1{\@/usr/bin/env@d}" \
%{buildroot}%{_datadir}/%{prj_name}/samples/python/benchmark/bert_benchmark/bert_benchmark.py \