-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from upstream/master #2
base: master
Are you sure you want to change the base?
Commits on Oct 24, 2024
-
Configuration menu - View commit details
-
Copy full SHA for c202882 - Browse repository at this point
Copy the full SHA c202882View commit details -
Bump actions/checkout from 4.1.7 to 4.2.2 (#27214)
Bumps [actions/checkout](https://github.com/actions/checkout) from 4.1.7 to 4.2.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/releases">actions/checkout's releases</a>.</em></p> <blockquote> <h2>v4.2.2</h2> <h2>What's Changed</h2> <ul> <li><code>url-helper.ts</code> now leverages well-known environment variables by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1941">actions/checkout#1941</a></li> <li>Expand unit test coverage for <code>isGhes</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1946">actions/checkout#1946</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4.2.1...v4.2.2">https://github.com/actions/checkout/compare/v4.2.1...v4.2.2</a></p> <h2>v4.2.1</h2> <h2>What's Changed</h2> <ul> <li>Check out other refs/* by commit if provided, fall back to ref by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1924">actions/checkout#1924</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/Jcambass"><code>@Jcambass</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1919">actions/checkout#1919</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4.2.0...v4.2.1">https://github.com/actions/checkout/compare/v4.2.0...v4.2.1</a></p> <h2>v4.2.0</h2> <h2>What's Changed</h2> <ul> <li>Add Ref and Commit outputs by <a href="https://github.com/lucacome"><code>@lucacome</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1180">actions/checkout#1180</a></li> <li>Dependabot updates in <a href="https://redirect.github.com/actions/checkout/pull/1777">actions/checkout#1777</a> & <a href="https://redirect.github.com/actions/checkout/pull/1872">actions/checkout#1872</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/yasonk"><code>@yasonk</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1869">actions/checkout#1869</a></li> <li><a href="https://github.com/lucacome"><code>@lucacome</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1180">actions/checkout#1180</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4.1.7...v4.2.0">https://github.com/actions/checkout/compare/v4.1.7...v4.2.0</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/blob/main/CHANGELOG.md">actions/checkout's changelog</a>.</em></p> <blockquote> <h1>Changelog</h1> <h2>v4.2.2</h2> <ul> <li><code>url-helper.ts</code> now leverages well-known environment variables by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1941">actions/checkout#1941</a></li> <li>Expand unit test coverage for <code>isGhes</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1946">actions/checkout#1946</a></li> </ul> <h2>v4.2.1</h2> <ul> <li>Check out other refs/* by commit if provided, fall back to ref by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1924">actions/checkout#1924</a></li> </ul> <h2>v4.2.0</h2> <ul> <li>Add Ref and Commit outputs by <a href="https://github.com/lucacome"><code>@lucacome</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1180">actions/checkout#1180</a></li> <li>Dependency updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>- <a href="https://redirect.github.com/actions/checkout/pull/1777">actions/checkout#1777</a>, <a href="https://redirect.github.com/actions/checkout/pull/1872">actions/checkout#1872</a></li> </ul> <h2>v4.1.7</h2> <ul> <li>Bump the minor-npm-dependencies group across 1 directory with 4 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1739">actions/checkout#1739</a></li> <li>Bump actions/checkout from 3 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1697">actions/checkout#1697</a></li> <li>Check out other refs/* by commit by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1774">actions/checkout#1774</a></li> <li>Pin actions/checkout's own workflows to a known, good, stable version. by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1776">actions/checkout#1776</a></li> </ul> <h2>v4.1.6</h2> <ul> <li>Check platform to set archive extension appropriately by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1732">actions/checkout#1732</a></li> </ul> <h2>v4.1.5</h2> <ul> <li>Update NPM dependencies by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1703">actions/checkout#1703</a></li> <li>Bump github/codeql-action from 2 to 3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1694">actions/checkout#1694</a></li> <li>Bump actions/setup-node from 1 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1696">actions/checkout#1696</a></li> <li>Bump actions/upload-artifact from 2 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1695">actions/checkout#1695</a></li> <li>README: Suggest <code>user.email</code> to be <code>41898282+github-actions[bot]@users.noreply.github.com</code> by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1707">actions/checkout#1707</a></li> </ul> <h2>v4.1.4</h2> <ul> <li>Disable <code>extensions.worktreeConfig</code> when disabling <code>sparse-checkout</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1692">actions/checkout#1692</a></li> <li>Add dependabot config by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1688">actions/checkout#1688</a></li> <li>Bump the minor-actions-dependencies group with 2 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1693">actions/checkout#1693</a></li> <li>Bump word-wrap from 1.2.3 to 1.2.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1643">actions/checkout#1643</a></li> </ul> <h2>v4.1.3</h2> <ul> <li>Check git version before attempting to disable <code>sparse-checkout</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1656">actions/checkout#1656</a></li> <li>Add SSH user parameter by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1685">actions/checkout#1685</a></li> <li>Update <code>actions/checkout</code> version in <code>update-main-version.yml</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1650">actions/checkout#1650</a></li> </ul> <h2>v4.1.2</h2> <ul> <li>Fix: Disable sparse checkout whenever <code>sparse-checkout</code> option is not present <a href="https://github.com/dscho"><code>@dscho</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1598">actions/checkout#1598</a></li> </ul> <h2>v4.1.1</h2> <ul> <li>Correct link to GitHub Docs by <a href="https://github.com/peterbe"><code>@peterbe</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1511">actions/checkout#1511</a></li> <li>Link to release page from what's new section by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1514">actions/checkout#1514</a></li> </ul> <h2>v4.1.0</h2> <ul> <li><a href="https://redirect.github.com/actions/checkout/pull/1396">Add support for partial checkout filters</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/actions/checkout/commit/11bd71901bbe5b1630ceea73d27597364c9af683"><code>11bd719</code></a> Prepare 4.2.2 Release (<a href="https://redirect.github.com/actions/checkout/issues/1953">#1953</a>)</li> <li><a href="https://github.com/actions/checkout/commit/e3d2460bbb42d7710191569f88069044cfb9d8cf"><code>e3d2460</code></a> Expand unit test coverage (<a href="https://redirect.github.com/actions/checkout/issues/1946">#1946</a>)</li> <li><a href="https://github.com/actions/checkout/commit/163217dfcd28294438ea1c1c149cfaf66eec283e"><code>163217d</code></a> <code>url-helper.ts</code> now leverages well-known environment variables. (<a href="https://redirect.github.com/actions/checkout/issues/1941">#1941</a>)</li> <li><a href="https://github.com/actions/checkout/commit/eef61447b9ff4aafe5dcd4e0bbf5d482be7e7871"><code>eef6144</code></a> Prepare 4.2.1 release (<a href="https://redirect.github.com/actions/checkout/issues/1925">#1925</a>)</li> <li><a href="https://github.com/actions/checkout/commit/6b42224f41ee5dfe5395e27c8b2746f1f9955030"><code>6b42224</code></a> Add workflow file for publishing releases to immutable action package (<a href="https://redirect.github.com/actions/checkout/issues/1919">#1919</a>)</li> <li><a href="https://github.com/actions/checkout/commit/de5a000abf73b6f4965bd1bcdf8f8d94a56ea815"><code>de5a000</code></a> Check out other refs/* by commit if provided, fall back to ref (<a href="https://redirect.github.com/actions/checkout/issues/1924">#1924</a>)</li> <li><a href="https://github.com/actions/checkout/commit/d632683dd7b4114ad314bca15554477dd762a938"><code>d632683</code></a> Prepare 4.2.0 release (<a href="https://redirect.github.com/actions/checkout/issues/1878">#1878</a>)</li> <li><a href="https://github.com/actions/checkout/commit/6d193bf28034eafb982f37bd894289fe649468fc"><code>6d193bf</code></a> Bump braces from 3.0.2 to 3.0.3 (<a href="https://redirect.github.com/actions/checkout/issues/1777">#1777</a>)</li> <li><a href="https://github.com/actions/checkout/commit/db0cee9a514becbbd4a101a5fbbbf47865ee316c"><code>db0cee9</code></a> Bump the minor-npm-dependencies group across 1 directory with 4 updates (<a href="https://redirect.github.com/actions/checkout/issues/1872">#1872</a>)</li> <li><a href="https://github.com/actions/checkout/commit/b6849436894e144dbce29d7d7fda2ae3bf9d8365"><code>b684943</code></a> Add Ref and Commit outputs (<a href="https://redirect.github.com/actions/checkout/issues/1180">#1180</a>)</li> <li>Additional commits viewable in <a href="https://github.com/actions/checkout/compare/v4.1.7...11bd71901bbe5b1630ceea73d27597364c9af683">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/checkout&package-manager=github_actions&previous-version=4.1.7&new-version=4.2.2)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for dd55426 - Browse repository at this point
Copy the full SHA dd55426View commit details -
Revert "[GPU] Increasing conditions for using fake_aligned shapes (#2…
…6450)" (#27211) This reverts commit 03aaa41. ### Tickets: - *[155861](https://jira.devtools.intel.com/browse/CVS-155861)*
Configuration menu - View commit details
-
Copy full SHA for 27780a6 - Browse repository at this point
Copy the full SHA 27780a6View commit details -
[RISCV64] add nhwc layout support for eltwise executor (#26531)
### Details: - *Add `nhwc` layout support for shl eltwise executor* - *Enable some tests with `nhwc` layout* ### Tickets: - *N/A*
Configuration menu - View commit details
-
Copy full SHA for 2a9c69d - Browse repository at this point
Copy the full SHA 2a9c69dView commit details -
[GPU][TESTS] Fix weightless caching tests (#27163)
Currently the tests have weightless caching enabled, but the models tested contain no constants eligible for weightless caching. This fixes the situation. To elaborate - all the models have f32 dtype constants by default. In these particular models all of the constants which would otherwise be eligible for weightless caching undergo some precision transformation which invalidates this eligibilty. The PR changes the dtype of the constants to prevent that and deletes the models which contain no constants eligible for weightless caching even after the dtype change.
Configuration menu - View commit details
-
Copy full SHA for 17f1601 - Browse repository at this point
Copy the full SHA 17f1601View commit details -
[intel-npu] Implementing LUID property in npu plugin (#27091)
### Details: - Implements ov::device::LUID property in npu_plugin (works on windows only) ### Tickets: - EISW-140889
Configuration menu - View commit details
-
Copy full SHA for 65a8f39 - Browse repository at this point
Copy the full SHA 65a8f39View commit details -
[GPU] Handle runtime scale value for PagedAttention (#27204)
### Details: - Add support for non-constant scale input, as the current Paged Attention specification does not require this value to be strictly constant
Configuration menu - View commit details
-
Copy full SHA for de66f0e - Browse repository at this point
Copy the full SHA de66f0eView commit details -
[Transformations] Fix vector subscript out of range in transformations (
#27180) ### Details: - Fix issue reported by MSVC `Assertion failed: vector subscript out of range` by skip accessing not existing parameters in `RemoveMultiSubGraphOpDanglingParamsResults` transformation. ### Tickets: - CVS-155258
Configuration menu - View commit details
-
Copy full SHA for d96bd7d - Browse repository at this point
Copy the full SHA d96bd7dView commit details -
[Core/Ref] Multiclass NMS: Fix vector initialization (#27157)
### Details: - `std::vector` initialized with actual size needed. ### Tickets: - CVS-155037
Configuration menu - View commit details
-
Copy full SHA for ea04212 - Browse repository at this point
Copy the full SHA ea04212View commit details -
[Pytorch fronted]: Added support for Search Sorted op (#26976)
### Details: - Added support for SearchSorted op with unittest. ### Tickets: - *[CVS-154559](https://jira.devtools.intel.com/browse/CVS-154559)* Depends on: - #26958 - #27036 --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com> Co-authored-by: Pawel Raasz <pawel.raasz@intel.com> Co-authored-by: Andrey Babushkin <andrey.babushkin@intel.com> Co-authored-by: Alicja Miloszewska <alicja.miloszewska@intel.com> Co-authored-by: Bogdan Pereanu <bogdan.pereanu@intel.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> Co-authored-by: Anastasiya(Asya) Pronina <anastasiya.pronina@intel.com> Co-authored-by: Dmitry Matveev <dmitry.matveev@intel.com> Co-authored-by: Andrei Beleiu <andrei-marin.beleiu@intel.com> Co-authored-by: Andrew Kwangwoong Park <andrew.park@intel.com> Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com> Co-authored-by: Pavel Durandin <pavel.durandin@intel.com> Co-authored-by: Alexey Smirnov <alexey.smirnov@intel.com> Co-authored-by: Hubert Błaszczyk <56601011+hub-bla@users.noreply.github.com> Co-authored-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com> Co-authored-by: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com> Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com> Co-authored-by: Andrzej Kopytko <andrzejx.kopytko@intel.com> Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> Co-authored-by: Alina Kladieva <alina.kladieva@intel.com> Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com> Co-authored-by: Maxim Vafin <maxim.vafin@intel.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6a8a69c - Browse repository at this point
Copy the full SHA 6a8a69cView commit details -
[DOCS] Adding GenAI Use Cases (#27062)
Creating an article with use case scenarios for using OpenVINO GenAI. This PR addresses the following JIRA ticket: CVS-153319 --------- Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3c0005e - Browse repository at this point
Copy the full SHA 3c0005eView commit details -
[PyOV] Extend Python API with SearchSorted-15 (#27230)
### Details: - *[PyOV] Extend Python API with SearchSorted-15* - *...* ### Tickets: - *CVS-155961*
Configuration menu - View commit details
-
Copy full SHA for 8faeed1 - Browse repository at this point
Copy the full SHA 8faeed1View commit details -
### Details: - OpenCV is NPU dependency only for single-image-test and protopipe. Since both NPU tools has moved to OpenVINO, for easier synchronization, we need to version OpenCV in OpenVINO NPU project ### Tickets: - E-143100
Configuration menu - View commit details
-
Copy full SHA for 104fe03 - Browse repository at this point
Copy the full SHA 104fe03View commit details -
[TESTS] Remove unused requirements.txt (#27235)
### Details: - *requirements.txt from pytorch hub tests are unused after #26856 * ### Tickets: - *CVS-155878*
Configuration menu - View commit details
-
Copy full SHA for 9b377f4 - Browse repository at this point
Copy the full SHA 9b377f4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 433e44e - Browse repository at this point
Copy the full SHA 433e44eView commit details -
Fixed vcpkg Android ARM64 build with ONNX 1.16.2 (#27217)
Replacement for #27171 JIRA CVS-155558
Configuration menu - View commit details
-
Copy full SHA for 79b0bad - Browse repository at this point
Copy the full SHA 79b0badView commit details
Commits on Oct 25, 2024
-
[GPU] Use impls cache in case when shape changed (#27226)
### Details: - Allow checking impls cache & running async compile when primitive shape is changed to improve the performance ### Tickets: - *CVS-155869*
Configuration menu - View commit details
-
Copy full SHA for 7098764 - Browse repository at this point
Copy the full SHA 7098764View commit details -
[GPU] Weightless caching - propagate weights_path from IR FE to the p…
…lugin (#27162) This PR is an implementation of an idea requested in this discussion: #25731 (comment).
Configuration menu - View commit details
-
Copy full SHA for a9dee49 - Browse repository at this point
Copy the full SHA a9dee49View commit details -
[GPU] Fixes for hybrid quantization (#27127)
### Details: - set LPT callbacks to handle compression and avoid constant folding for it (taken from #20973) - Allow u8/i8 output data type for compressed onednn FC - Disable Dequantize propagation through Transpose if it's a dependency of SDPA to keep Transpose+SDPA fusion
Configuration menu - View commit details
-
Copy full SHA for c21f572 - Browse repository at this point
Copy the full SHA c21f572View commit details -
[CPU][ARM64] Add JIT emitter for Eltwise Greater operation (#27145)
### Details: - Added a jit_greater_emitter derived class in aarch64/jit_eltwise_emitters - Created entry Algorithm::EltwiseGreater in the get_supported_precisions in nodes/kernels/aarch64 - Add the EltwiseGreater entry in the aarch64 executors supported algorithms ### Tickets: - Closes: #24421 Signed-off-by: Nashez Zubair <nashezzubair@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for e19724e - Browse repository at this point
Copy the full SHA e19724eView commit details -
[ref]: SearchSorted: Made ref impl parallel. (#27181)
### Details: - Made ref impl parallel. Scaling is done via values space. ### Tickets: - *CVS-155707* Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for c8415c3 - Browse repository at this point
Copy the full SHA c8415c3View commit details -
Bump actions/cache from 4.1.1 to 4.1.2 (#27242)
Bumps [actions/cache](https://github.com/actions/cache) from 4.1.1 to 4.1.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/cache/releases">actions/cache's releases</a>.</em></p> <blockquote> <h2>v4.1.2</h2> <h2>What's Changed</h2> <ul> <li>Add Bun example by <a href="https://github.com/idleberg"><code>@idleberg</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1456">actions/cache#1456</a></li> <li>Revise <code>isGhes</code> logic by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1474">actions/cache#1474</a></li> <li>Bump braces from 3.0.2 to 3.0.3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1475">actions/cache#1475</a></li> <li>Add dependabot.yml to enable automatic dependency upgrades by <a href="https://github.com/Link"><code>@Link</code></a>- in <a href="https://redirect.github.com/actions/cache/pull/1476">actions/cache#1476</a></li> <li>Bump actions/checkout from 3 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1478">actions/cache#1478</a></li> <li>Bump actions/stale from 3 to 9 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1479">actions/cache#1479</a></li> <li>Bump github/codeql-action from 2 to 3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1483">actions/cache#1483</a></li> <li>Bump actions/setup-node from 3 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/cache/pull/1481">actions/cache#1481</a></li> <li>Prepare <code>4.1.2</code> release by <a href="https://github.com/Link"><code>@Link</code></a>- in <a href="https://redirect.github.com/actions/cache/pull/1477">actions/cache#1477</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/idleberg"><code>@idleberg</code></a> made their first contribution in <a href="https://redirect.github.com/actions/cache/pull/1456">actions/cache#1456</a></li> <li><a href="https://github.com/jww3"><code>@jww3</code></a> made their first contribution in <a href="https://redirect.github.com/actions/cache/pull/1474">actions/cache#1474</a></li> <li><a href="https://github.com/Link"><code>@Link</code></a>- made their first contribution in <a href="https://redirect.github.com/actions/cache/pull/1476">actions/cache#1476</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/cache/compare/v4...v4.1.2">https://github.com/actions/cache/compare/v4...v4.1.2</a></p> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/actions/cache/blob/main/RELEASES.md">actions/cache's changelog</a>.</em></p> <blockquote> <h1>Releases</h1> <h3>4.1.2</h3> <ul> <li>Add GitHub Enterprise Cloud instances hostname filters to inform API endpoint choices - <a href="https://redirect.github.com/actions/cache/pull/1474">#1474</a></li> <li>Security fix: Bump braces from 3.0.2 to 3.0.3 - <a href="https://redirect.github.com/actions/cache/pull/1475">#1475</a></li> </ul> <h3>4.1.1</h3> <ul> <li>Restore original behavior of <code>cache-hit</code> output - <a href="https://redirect.github.com/actions/cache/pull/1467">#1467</a></li> </ul> <h3>4.1.0</h3> <ul> <li>Ensure <code>cache-hit</code> output is set when a cache is missed - <a href="https://redirect.github.com/actions/cache/pull/1404">#1404</a></li> <li>Deprecate <code>save-always</code> input - <a href="https://redirect.github.com/actions/cache/pull/1452">#1452</a></li> </ul> <h3>4.0.2</h3> <ul> <li>Fixed restore <code>fail-on-cache-miss</code> not working.</li> </ul> <h3>4.0.1</h3> <ul> <li>Updated <code>isGhes</code> check</li> </ul> <h3>4.0.0</h3> <ul> <li>Updated minimum runner version support from node 12 -> node 20</li> </ul> <h3>3.3.3</h3> <ul> <li>Updates <code>@actions/cache</code> to v3.2.3 to fix accidental mutated path arguments to <code>getCacheVersion</code> <a href="https://redirect.github.com/actions/toolkit/pull/1378">actions/toolkit#1378</a></li> <li>Additional audit fixes of npm package(s)</li> </ul> <h3>3.3.2</h3> <ul> <li>Fixes bug with Azure SDK causing blob downloads to get stuck.</li> </ul> <h3>3.3.1</h3> <ul> <li>Reduced segment size to 128MB and segment timeout to 10 minutes to fail fast in case the cache download is stuck.</li> </ul> <h3>3.3.0</h3> <ul> <li>Added option to lookup cache without downloading it.</li> </ul> <h3>3.2.6</h3> <ul> <li>Fix zstd not being used after zstd version upgrade to 1.5.4 on hosted runners.</li> </ul> <h3>3.2.5</h3> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/actions/cache/commit/6849a6489940f00c2f30c0fb92c6274307ccb58a"><code>6849a64</code></a> Release 4.1.2 <a href="https://redirect.github.com/actions/cache/issues/1477">#1477</a></li> <li><a href="https://github.com/actions/cache/commit/5a1720c49e91718f5d0ce7f154997c93e0f6159a"><code>5a1720c</code></a> Merge branch 'Link-/prep-4.1.2' of <a href="https://github.com/actions/cache">https://github.com/actions/cache</a> into Link...</li> <li><a href="https://github.com/actions/cache/commit/d9fef48d24d529bac46adcc1e42f49649de07ca9"><code>d9fef48</code></a> Merge branch 'main' into Link-/prep-4.1.2</li> <li><a href="https://github.com/actions/cache/commit/a50e8d027b022a55ef85ffa721ebd97d2b22bcda"><code>a50e8d0</code></a> Merge branch 'main' into Link-/prep-4.1.2</li> <li><a href="https://github.com/actions/cache/commit/acc9ae5c1401b6c072a7c89ff4c48ea7e30f4dbf"><code>acc9ae5</code></a> Merge pull request <a href="https://redirect.github.com/actions/cache/issues/1481">#1481</a> from actions/dependabot/github_actions/actions/setup...</li> <li><a href="https://github.com/actions/cache/commit/1ea5f18c31265ef251b3eb51ce8b857be5e7b044"><code>1ea5f18</code></a> Merge branch 'main' into Link-/prep-4.1.2</li> <li><a href="https://github.com/actions/cache/commit/cc679ff3baee71867c711040a5c21af61b262806"><code>cc679ff</code></a> Merge branch 'main' into dependabot/github_actions/actions/setup-node-4</li> <li><a href="https://github.com/actions/cache/commit/366d43d6f8aa1f3e5d28b2c98959d557d78ffa3f"><code>366d43d</code></a> Merge pull request <a href="https://redirect.github.com/actions/cache/issues/1483">#1483</a> from actions/dependabot/github_actions/github/codeql...</li> <li><a href="https://github.com/actions/cache/commit/02bf31969bcc471fd5f91b5896ae17beb0973413"><code>02bf319</code></a> Bump github/codeql-action from 2 to 3</li> <li><a href="https://github.com/actions/cache/commit/6f6220be5af96ba6940aca960265218cae17e8fd"><code>6f6220b</code></a> Merge branch 'main' into dependabot/github_actions/actions/setup-node-4</li> <li>Additional commits viewable in <a href="https://github.com/actions/cache/compare/3624ceb22c1c5a301c8db4169662070a689d9ea8...6849a6489940f00c2f30c0fb92c6274307ccb58a">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/cache&package-manager=github_actions&previous-version=4.1.1&new-version=4.1.2)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 051e676 - Browse repository at this point
Copy the full SHA 051e676View commit details -
Support for INT4 decompression patterns from NNCF (#27048)
### Details: - [torch.compile] Added translation decompression subgraph to u4 in `translate_stack_fx` - [torch.compile] Added capture NNCF INT4 decompression patterns in `make_partitions` - [pytorch frontend] Added ov::frontend::pytorch::pass::U4ConvertReshape transformation to support NNCF INT4 decompression patterns ![U4ConvertReshape](https://github.com/user-attachments/assets/b25d5e89-047d-4ee6-a850-45e87fad66f8) - Updated `u4_compression_stack` transformation to support Torch FX flow. ### Tickets: - ref: 153918
Configuration menu - View commit details
-
Copy full SHA for f1dc976 - Browse repository at this point
Copy the full SHA f1dc976View commit details -
[GPU] add XE3 to build (#26811)
- update cmake to add xe3 - update onednn rls-v3.7-pc
Configuration menu - View commit details
-
Copy full SHA for 9404819 - Browse repository at this point
Copy the full SHA 9404819View commit details -
[GHA] Increase timeout for PyTorch Models tests in precommit (#27247)
### Tickets: - 155619
Configuration menu - View commit details
-
Copy full SHA for 8d6f517 - Browse repository at this point
Copy the full SHA 8d6f517View commit details -
[Transformation] LoraSubgraph fusion (#27068)
### Details: - *Introduced `LoraSubgraph` operation, which is used for LoRA subgraphs fusion for further optimizations (for the details, please refer to the description in the header)* - *Introduced `LoraSubgraphFusion` pass* - *The changes are covered by transformation tests* ### Tickets: - *CVS-153035* - *CVS-155112*
Configuration menu - View commit details
-
Copy full SHA for 2daa8b9 - Browse repository at this point
Copy the full SHA 2daa8b9View commit details -
[ONNX] Switched to ONNX 1.17.0 (#26916)
### Details: - Switched to ONNX 1.17.0 ### Tickets: - N/A
Configuration menu - View commit details
-
Copy full SHA for 326dfa0 - Browse repository at this point
Copy the full SHA 326dfa0View commit details -
[CPU] Add per-token asym INT8 dynamic quantization support to QKV/MLP…
… node (#27001) ### Details: - to use AMX-INT8 to boost performance of QKV/MLP layers in LLM, we need dynamic per-token INT8 quantization according to many research papers (SmoothQuant for example) and reference implementations (xFT for example), here we add the support, when following conditions are met: - platform support AMX-INT8 - QKV&MLP weights are symmetrically per-OC quantized as INT8 - add AMX-FP16 support to QKV/MLP layers on GNR platform. - optimize single batch 2nd token special case. ### Tickets: - *ticket-id* --------- Signed-off-by: Luo Cheng <cheng.luo@intel.com> Co-authored-by: Luo Cheng <cheng.luo@intel.com>
Configuration menu - View commit details
-
Copy full SHA for e279492 - Browse repository at this point
Copy the full SHA e279492View commit details -
[Opset15] Finalize Opset15 (#27141)
### Details: - Finalize Opset15 with remaining ops - Update python api, opset15_tbl and docs ### Tickets: - 138273 --------- Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3dfebf8 - Browse repository at this point
Copy the full SHA 3dfebf8View commit details -
[CPU][ACL] Refactor weights packaging in ACL FC executor (#27065)
### Details: - Fixed issue: empty `arm_compute::WeightsInfo` was passed into `has_opt_impl`, so preferred weight format was never selected. - Performance improved: ACL reorder, transpose and convert were replaced with oneDNN primitives. TODO: - [x] Run performance checks ### Tickets: - CVS-155912
Configuration menu - View commit details
-
Copy full SHA for 2f3a93e - Browse repository at this point
Copy the full SHA 2f3a93eView commit details -
[Transformations] SharedOpOptimization and SymbolicOptimization update (
#27243) ### Details: - SharedOpOptimization: optimization keeps the same topological order. It allows for seamless optimization in one run over the model - OptimizeSymbolsUsedAsValues: partial values containing symbols and constant values are now participating in the value optimization too - Continuation of PR 27153 to fix tests ### Tickets: - N/A ### Related PR: - #27153 --------- Co-authored-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 884ac4a - Browse repository at this point
Copy the full SHA 884ac4aView commit details -
NPUW: Introduce 'last' keyword for dump options (#26841)
### Details: - The problem is that for different networks the number of NPUW's detected block may be different and it is hard to tell what the last block number will be. Now 'last' option can be used to tell NPUW to dump tail block without setting specific number. ### Tickets: - E-139857
Configuration menu - View commit details
-
Copy full SHA for 8934f90 - Browse repository at this point
Copy the full SHA 8934f90View commit details -
[TF FE] Stabilize tests for RandomUniform and RandomUniformInt on all…
… platforms (#26921) **Details:** Stabilize tests for RandomUniform and RandomUniformInt on all platforms **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3af0e9e - Browse repository at this point
Copy the full SHA 3af0e9eView commit details -
[PyOV] Remove
py
package (#27248)### Details: - `py` package has a high CVE on it - it's also in maintenance mode - there are seemingly no usages of that package in the codebase, so it can be dropped - let's wait for CI results to confirm ### Tickets: - CVS-156002
Configuration menu - View commit details
-
Copy full SHA for 0f067ae - Browse repository at this point
Copy the full SHA 0f067aeView commit details -
NPUW: Handle closures just once for single-shot functions (#27132)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 899886e - Browse repository at this point
Copy the full SHA 899886eView commit details -
Fix protopipe dependencies for Linux (#27249)
### Details: - winmm is Windows only dependency ### Tickets: - E-144853
Configuration menu - View commit details
-
Copy full SHA for 00955e2 - Browse repository at this point
Copy the full SHA 00955e2View commit details -
[docs] Security badges addition (#27253)
### Details: - Added new section with security badges ### Tickets: - 155982
Configuration menu - View commit details
-
Copy full SHA for 34f3308 - Browse repository at this point
Copy the full SHA 34f3308View commit details -
NPU: Don't update command list if set_tensor is called with the same …
…tensor (#27239) ### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for a4f4e78 - Browse repository at this point
Copy the full SHA a4f4e78View commit details -
Added a Wheels section to the Python Build Docs (#26728)
### Details: - *Included explanation about python wheels and the wheels built by OpenVINO. Updated the Linux build example to include cloning the repo that was missing earlier* ### Tickets: - *22017* --------- Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com> Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 361cf2c - Browse repository at this point
Copy the full SHA 361cf2cView commit details -
[GHA] Fixed Win debug pipeline (#27056)
### Details: - Fixed Debug build by setting the right build_type - Skipped long functional tests - skipped failed tests ### Tickets: - *155031*
Configuration menu - View commit details
-
Copy full SHA for 094c0b9 - Browse repository at this point
Copy the full SHA 094c0b9View commit details -
Build yaml-cpp statically (#27251)
### Details: - no need to build dynamic yaml-cpp library. Overlooked while moving it from npu project https://github.com/openvinotoolkit/npu_plugin/blob/develop/thirdparty/CMakeLists.txt#L27 - before ``` Creating library C:/Users/mdoronin/work/openvino/bin/intel64/Release/yaml-cpp.lib and object C:/Users/mdoronin/work/openvino/bin/intel64/Release/yaml-cpp.exp yaml-cpp.vcxproj -> C:\Users\mdoronin\work\openvino\bin\intel64\Release\yaml-cpp.dll ``` - after ``` yaml-cpp.vcxproj -> C:\Users\mdoronin\work\openvino\bin\intel64\Release\yaml-cpp.lib ``` ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 797b441 - Browse repository at this point
Copy the full SHA 797b441View commit details -
[TESTS] Update torch hub tests for export scenario (#27236)
### Details: - *Update timm to 1.0.11 and the model list accordingly* - *Update marks in accordance with recent improvements in export support* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 2fae7bc - Browse repository at this point
Copy the full SHA 2fae7bcView commit details -
[STFT][CPU] Add STFT op to CPU and enable by ref (#27137)
### Details: - Enablement of STFT op in CPU by ref impl - Including support for dynamic shapes, and shape related inputs as Parameters ** There is ongoing work to reuse RDFT Executor within STFT CPU impl. Due to number of needed changes, decided to enable by ref first. ### Tickets: - 147161 Related PR: - #27186
Configuration menu - View commit details
-
Copy full SHA for 2d3289e - Browse repository at this point
Copy the full SHA 2d3289eView commit details -
NPUW: Extend HostGather to more cases (#27138)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for f413806 - Browse repository at this point
Copy the full SHA f413806View commit details
Commits on Oct 26, 2024
-
[DOC] Composability of different threading runtimes (#26950)
### Details: - *Document composability of different threading runtimes when running inferences and other application logic on CPU device* - *Document threading impact for LLM with Optimum Intel API* ### Tickets: - *CVS-150542, CVS-145996* --------- Signed-off-by: Chen, Peter <peter.chen@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 0c07136 - Browse repository at this point
Copy the full SHA 0c07136View commit details -
Mark mandatory conformance tests for HW plugins (#27197)
### Details: - *Mark OVHoldersTestOnImportedNetwork and OVClassQueryModelTest mandatory for HW plugin and optional for meta-plugin* - *Remove the meta-plugin skipping in test cases* ### Tickets: - *CVS-130212* --------- Signed-off-by: Chen, Peter <peter.chen@intel.com> Co-authored-by: panhaiqi <haiqi.pan@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f3e3f75 - Browse repository at this point
Copy the full SHA f3e3f75View commit details
Commits on Oct 27, 2024
-
Remove duplicate backend registration from torch 2.5 (#27245)
### Details: - In torch 2.5.0, pytorch is registering the backends from entrypoints and we don't have to register the backend again. If we register it twice, torch throws a duplicate registration error. ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 4a33ad8 - Browse repository at this point
Copy the full SHA 4a33ad8View commit details -
[OVC] Fail with unsupported message when output argument is used for …
Configuration menu - View commit details
-
Copy full SHA for afa9231 - Browse repository at this point
Copy the full SHA afa9231View commit details
Commits on Oct 28, 2024
-
[GPU] Support convolution onednn activation zero points for i32 (#27261)
### Details: - Support activation zero points for i32 in convolution onednn ### Tickets: - 155423
Configuration menu - View commit details
-
Copy full SHA for 65dd174 - Browse repository at this point
Copy the full SHA 65dd174View commit details -
Add "if" statement for loop unrolling in rms kernel. (#27215)
### Details: - *Add "if" statement for loop unrolling in rms kernel to fix Segmentation Fault in tiny-random-sd3 model* ### Tickets: - *CVS-152057*
Configuration menu - View commit details
-
Copy full SHA for 78864ca - Browse repository at this point
Copy the full SHA 78864caView commit details -
[RV64] Disabled multi-stream mode when SHL is used (#27250)
### Details: - *SHL library uses static global variables as flags and counters. It means that multi-stream execution can be unsafe when SHL is used - there can be data racing. The PR manually sets `streams = 1` to avoid possible functional issues in tput scenario with using SHL* ### Tickets: - *N/A*
Configuration menu - View commit details
-
Copy full SHA for 9b97cf9 - Browse repository at this point
Copy the full SHA 9b97cf9View commit details -
[TF FE][JAX FE] Support latest TF 2.18, JAX 0.4.35 and NumPy 2.x (#27246
Configuration menu - View commit details
-
Copy full SHA for 8bc1655 - Browse repository at this point
Copy the full SHA 8bc1655View commit details -
[RV64] Added build support via linux package and fix the build via GN…
…U toolchain (#27228) ### Details: - *The [GNU toolchain for RISC-V](https://github.com/riscv-collab/riscv-gnu-toolchain) now supports RVV by default - ratified RVV1.0. All intrinsics have prefix `__riscv64`. Some compilers (clang, llvm) can compile a code contained intrinsics without this prefix (have overloaded functions). But GCC from `riscv-gnu-toolchain` doesn't have them - so cannot compile max pooling primitive from oneDNN. The fix in oneDNN* - openvinotoolkit/oneDNN#265 - *Added one more option to cross-compile OpenVINO for riscv64 platforms without RVV - using linux packages and new written cmake toolchain file* - *Renamed `T-Head` to `Xuantie`* - *Added the information about recommended build to tutorial* ### Tickets: - *N/A*
Configuration menu - View commit details
-
Copy full SHA for de5f765 - Browse repository at this point
Copy the full SHA de5f765View commit details -
[PyOV] Migrate from direct setup.py calls in Benchmark App and Docs CI (
#27220) ### Details: - Remove direct `setup.py` calls from comments in cmake files - Change the docs building command in GHA - Migrate Benchmark App wheel building command to use `python -m pip wheel .` - Since `openvino_dev` is deprecated and set to be removed soon anyway, the `constraints.txt` file has been unpinned from Benchmark App requirements. In my opinion this simplifies the code significantly with no drawbacks, because `numpy` version for benchmark_app (the only dependency) is not even specified in `constraints.txt`, which will soon be removed. ### Tickets: - CVS-155956 - CVS-155957 --------- Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6f001e9 - Browse repository at this point
Copy the full SHA 6f001e9View commit details -
Bump actions/setup-node from 4.0.4 to 4.1.0 (#27266)
Bumps [actions/setup-node](https://github.com/actions/setup-node) from 4.0.4 to 4.1.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/setup-node/releases">actions/setup-node's releases</a>.</em></p> <blockquote> <h2>v4.1.0</h2> <h2>What's Changed</h2> <ul> <li>Resolve High Security Alerts by upgrading Dependencies by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1132">actions/setup-node#1132</a></li> <li>Upgrade IA Publish by <a href="https://github.com/Jcambass"><code>@Jcambass</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1134">actions/setup-node#1134</a></li> <li>Revise <code>isGhes</code> logic by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1148">actions/setup-node#1148</a></li> <li>Add architecture to cache key by <a href="https://github.com/pengx17"><code>@pengx17</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/843">actions/setup-node#843</a> This addresses issues with caching by adding the architecture (arch) to the cache key, ensuring that cache keys are accurate to prevent conflicts. Note: This change may break previous cache keys as they will no longer be compatible with the new format.</li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/jww3"><code>@jww3</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-node/pull/1148">actions/setup-node#1148</a></li> <li><a href="https://github.com/pengx17"><code>@pengx17</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-node/pull/843">actions/setup-node#843</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/setup-node/compare/v4...v4.1.0">https://github.com/actions/setup-node/compare/v4...v4.1.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/actions/setup-node/commit/39370e3970a6d050c480ffad4ff0ed4d3fdee5af"><code>39370e3</code></a> fix: add arch to cached path (<a href="https://redirect.github.com/actions/setup-node/issues/843">#843</a>)</li> <li><a href="https://github.com/actions/setup-node/commit/abb238b1313d8ef4d3e3a96d204e08329cafbf85"><code>abb238b</code></a> Revise <code>isGhes</code> logic (<a href="https://redirect.github.com/actions/setup-node/issues/1148">#1148</a>)</li> <li><a href="https://github.com/actions/setup-node/commit/aca7b64a59c0063db8564e0ffdadd3887f1cbae5"><code>aca7b64</code></a> Merge pull request <a href="https://redirect.github.com/actions/setup-node/issues/1134">#1134</a> from actions/Jcambass-patch-1</li> <li><a href="https://github.com/actions/setup-node/commit/88de2a3d99c13aa734c49200e8bc673fb0a80ab8"><code>88de2a3</code></a> Resolve High Security Alerts by upgrading Dependencies (<a href="https://redirect.github.com/actions/setup-node/issues/1132">#1132</a>)</li> <li><a href="https://github.com/actions/setup-node/commit/d6ebc7b438e9cf1b22a3c440a164b179ed0e37d6"><code>d6ebc7b</code></a> Upgrade IA Publish</li> <li>See full diff in <a href="https://github.com/actions/setup-node/compare/0a44ba7841725637a19e28fa30b79a866c81b0a6...39370e3970a6d050c480ffad4ff0ed4d3fdee5af">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/setup-node&package-manager=github_actions&previous-version=4.0.4&new-version=4.1.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for f5ef9b6 - Browse repository at this point
Copy the full SHA f5ef9b6View commit details -
[STFT] Pytorch FE enablement of STFT operation (#27186)
### Details: - Pytorch FE enablement of STFT op - This PR contains STFT CPU enablement changes (to be merged first), please review pytorch related changes only within this PR: src/frontends/pytorch/src/op/stft.cpp + test_stft.py ### Tickets: - 155166, 143017 Related PR: - #27137 --------- Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 08365f6 - Browse repository at this point
Copy the full SHA 08365f6View commit details -
[TESTS] Update pytorch version to 2.5.0 (#27117)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 30a52e8 - Browse repository at this point
Copy the full SHA 30a52e8View commit details -
Bump actions/setup-python from 5.2.0 to 5.3.0 (#27267)
Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5.2.0 to 5.3.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/setup-python/releases">actions/setup-python's releases</a>.</em></p> <blockquote> <h2>v5.3.0</h2> <h2>What's Changed</h2> <ul> <li>Add workflow file for publishing releases to immutable action package by <a href="https://github.com/Jcambass"><code>@Jcambass</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/941">actions/setup-python#941</a></li> <li>Upgrade IA publish by <a href="https://github.com/Jcambass"><code>@Jcambass</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/943">actions/setup-python#943</a></li> </ul> <h3>Bug Fixes:</h3> <ul> <li>Normalise Line Endings to Ensure Cross-Platform Consistency by <a href="https://github.com/priya-kinthali"><code>@priya-kinthali</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/938">actions/setup-python#938</a></li> <li>Revise <code>isGhes</code> logic by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/963">actions/setup-python#963</a></li> <li>Bump pillow from 7.2 to 10.2.0 by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/956">actions/setup-python#956</a></li> </ul> <h3>Enhancements:</h3> <ul> <li>Enhance workflows and documentation updates by <a href="https://github.com/priya-kinthali"><code>@priya-kinthali</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/965">actions/setup-python#965</a></li> <li>Bump default versions to latest by <a href="https://github.com/jeffwidman"><code>@jeffwidman</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/905">actions/setup-python#905</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/Jcambass"><code>@Jcambass</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-python/pull/941">actions/setup-python#941</a></li> <li><a href="https://github.com/jww3"><code>@jww3</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-python/pull/963">actions/setup-python#963</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/setup-python/compare/v5...v5.3.0">https://github.com/actions/setup-python/compare/v5...v5.3.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/actions/setup-python/commit/0b93645e9fea7318ecaed2b359559ac225c90a2b"><code>0b93645</code></a> Enhance workflows: Add macOS 13 support, upgrade publish-action, and update d...</li> <li><a href="https://github.com/actions/setup-python/commit/9c76e716502b18322365741b762fee22a8cffad8"><code>9c76e71</code></a> Bump pillow from 7.2 to 10.2.0 in /<strong>tests</strong>/data (<a href="https://redirect.github.com/actions/setup-python/issues/956">#956</a>)</li> <li><a href="https://github.com/actions/setup-python/commit/f4c5a1183d69690d31b6304b7af403a5b56a88d6"><code>f4c5a11</code></a> Revise <code>isGhes</code> logic (<a href="https://redirect.github.com/actions/setup-python/issues/963">#963</a>)</li> <li><a href="https://github.com/actions/setup-python/commit/19dfb7b659fa9e60c2f89c33335ab5f6f1792b6e"><code>19dfb7b</code></a> Bump default versions to latest (<a href="https://redirect.github.com/actions/setup-python/issues/905">#905</a>)</li> <li><a href="https://github.com/actions/setup-python/commit/e9675cc634901ff55d92c575ecd6945e65464b00"><code>e9675cc</code></a> Merge pull request <a href="https://redirect.github.com/actions/setup-python/issues/943">#943</a> from actions/Jcambass-patch-1</li> <li><a href="https://github.com/actions/setup-python/commit/3226af69c08a4851edf81cffc8849d2db148b21f"><code>3226af6</code></a> Upgrade IA publish</li> <li><a href="https://github.com/actions/setup-python/commit/70dcb22d269dc9546a5d97f4b11548f130526421"><code>70dcb22</code></a> Merge pull request <a href="https://redirect.github.com/actions/setup-python/issues/941">#941</a> from actions/Jcambass-patch-1</li> <li><a href="https://github.com/actions/setup-python/commit/65b48c71155ac3186106d8d8de14787f5914b8d1"><code>65b48c7</code></a> Create publish-immutable-actions.yml</li> <li><a href="https://github.com/actions/setup-python/commit/29a37be0a3d3e8bf5bc1eb19cd0502922f5b312a"><code>29a37be</code></a> initial commit (<a href="https://redirect.github.com/actions/setup-python/issues/938">#938</a>)</li> <li>See full diff in <a href="https://github.com/actions/setup-python/compare/f677139bbe7f9c59b41e40162b753c062f5d49a3...0b93645e9fea7318ecaed2b359559ac225c90a2b">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=actions/setup-python&package-manager=github_actions&previous-version=5.2.0&new-version=5.3.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 443078c - Browse repository at this point
Copy the full SHA 443078cView commit details -
[GPU] Support GeLU Tanh for Phi-2 (#27213)
### Details: - Previously GeLU Tanh was supported only for x * (0.5 * (1 + tanh)) - Support pattern with (x * 0.5) * (1 + tanh)) too. ### Tickets: - 155576
Configuration menu - View commit details
-
Copy full SHA for 7a80fe8 - Browse repository at this point
Copy the full SHA 7a80fe8View commit details -
Update flake8-comprehensions requirement from <=3.15.0 to <=3.16.0 in…
… /src/bindings/python (#27268) Updates the requirements on [flake8-comprehensions](https://github.com/adamchainz/flake8-comprehensions) to permit the latest version. <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/adamchainz/flake8-comprehensions/blob/main/CHANGELOG.rst">flake8-comprehensions's changelog</a>.</em></p> <blockquote> <h2>3.16.0 (2024-10-27)</h2> <ul> <li> <p>Drop Python 3.8 support.</p> </li> <li> <p>Support Python 3.13.</p> </li> </ul> <h2>3.15.0 (2024-06-29)</h2> <ul> <li> <p>Add rule C420 to check for dict comprehensions with constant values, encouraging replacement with <code>dict.fromkeys()</code>.</p> <p>Thanks to Tom Kuson in <code>PR [#553](adamchainz/flake8-comprehensions#553) <https://github.com/adamchainz/flake8-comprehensions/pull/553></code>__.</p> </li> </ul> <h2>3.14.0 (2023-07-10)</h2> <ul> <li>Drop Python 3.7 support.</li> </ul> <h2>3.13.0 (2023-06-15)</h2> <ul> <li>Support Python 3.12.</li> </ul> <h2>3.12.0 (2023-04-13)</h2> <ul> <li> <p>Add rule C418 to check for calls passing a dict literal or dict comprehension to <code>dict()</code>.</p> </li> <li> <p>Add rule C419 to check for calls passing a list comprehension to <code>any()</code>/<code>all()</code>.</p> </li> </ul> <h2>3.11.1 (2023-03-21)</h2> <ul> <li> <p>Fix false positives in C406 “unnecessary dict literal”.</p> <p>Fixes <code>Issue [#260](adamchainz/flake8-comprehensions#260) <https://github.com/adamchainz/flake8-comprehensions/issues/260></code>__.</p> </li> </ul> <h2>3.11.0 (2023-03-18)</h2> <ul> <li> <p>Expand C416 to <code>dict</code> comprehensions.</p> <p>Thanks to Aaron Gokaslan in <code>PR [#490](adamchainz/flake8-comprehensions#490) <https://github.com/adamchainz/flake8-comprehensions/pull/490></code>__.</p> </li> </ul> <h2>3.10.1 (2022-10-29)</h2> <ul> <li>Fix false positive in rules C402 and C404 for <code>dict()</code> calls with keyword arguments.</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/bf5861b1b3d1eb1b661a34ae71db1a2bf80ced5d"><code>bf5861b</code></a> Version 3.16.0</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/bd8b05591006538f60602403dc2448e0c9c4f12d"><code>bd8b055</code></a> Drop Python 3.8 support (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/600">#600</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/cfba30c175ddc41f2a43a94cbffac013b9fccac1"><code>cfba30c</code></a> Add automated release process (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/601">#601</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/e49e753e5661e17a553d14a610f0807152d9f843"><code>e49e753</code></a> [pre-commit.ci] pre-commit autoupdate (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/599">#599</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/2bc3ccbe27502377a7fd244714f1ce1d6c2efc84"><code>2bc3ccb</code></a> Bump astral-sh/setup-uv from 1 to 3 in the github-actions group (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/598">#598</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/a7842a644ff573e5d567b52332fb5cb27889adaf"><code>a7842a6</code></a> Support Python 3.13 (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/597">#597</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/7df8477e2b055fdc1fd0ae51f2bed75152e54c8a"><code>7df8477</code></a> Upgrade requirements (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/596">#596</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/4272785a82e6603fac06c67ef9457d2a9a88550e"><code>4272785</code></a> Use uv on GitHub Actions (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/595">#595</a>)</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/a03d78f1845b6b3034f39b08eda3fba47af20fa7"><code>a03d78f</code></a> Move automatic updates to monthly</li> <li><a href="https://github.com/adamchainz/flake8-comprehensions/commit/5ea939475914a2a534bd302c4fe5f3e704c30c95"><code>5ea9394</code></a> [pre-commit.ci] pre-commit autoupdate (<a href="https://redirect.github.com/adamchainz/flake8-comprehensions/issues/594">#594</a>)</li> <li>Additional commits viewable in <a href="https://github.com/adamchainz/flake8-comprehensions/compare/1.0.0...3.16.0">compare view</a></li> </ul> </details> <br /> Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for dd6ed6c - Browse repository at this point
Copy the full SHA dd6ed6cView commit details -
[]NPU] Update adapter and backend to use new level zero ext table (#2…
…7095) ### Details: - *use ze_graph_dditable_ext_t to replace local ze_graph_dditable_ext_last_t* - *use ze_graph_ext_version_t as template parameter instead of ze_graph_dditable_ext_1_x* - *update commit of level-zero-ext to use one ddi table* Plugin with current driver and driver released later, will use ze_graph_dditable_ext_t and ZE_extension_graph, the version is ZE_GRAPH_EXT_VERSION_CURRENT inside current level-zero-ext commit, 1.8 now Plugin with old driver, will use ze_graph_dditable_ext_t to reinterpret old ddi table, use largest version supported by driver, , backend work on ze_graph_ext_version_t, compiler will work based on ze_graph_ext_version_t. Fpr example, largest ext version supported by driver is 1.7. plugin will use 1.7. ### Tickets: - *155313*
Configuration menu - View commit details
-
Copy full SHA for 8371289 - Browse repository at this point
Copy the full SHA 8371289View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2db556d - Browse repository at this point
Copy the full SHA 2db556dView commit details -
[GPU] Fix bugs in cpu impls (#27260)
### Details: - *Select GPU implementation for reorder in shape flow with blocked output format.* - *Ensure CPU implementation waits for GPU kernel execution to finish when using GPU output as input.* ### Tickets: - *155116*
Configuration menu - View commit details
-
Copy full SHA for 33493b4 - Browse repository at this point
Copy the full SHA 33493b4View commit details -
[STFT][Op][Ref] Extend STFT op and ref to support 1D signal input (#2…
…7274) ### Details: - Extend STFT op and ref to support 1D signal input (including CPU, as currently it uses ref impl) - Less code is needed to support such case natively than subgraph for proper Squeeze/Unsqueeze logic - For 1D signal enablement minor changes in shape_infer and ref impl have been added (all of the other updated files are tests): * src/core/reference/src/op/stft.cpp * src/core/shape_inference/include/stft_shape_inference.hpp - Xfail for 1D stft case for PT FE has been removed, the test passed --------------------------------- PR for spec update will be provided separately (in progress). ### Tickets: - 155996
Configuration menu - View commit details
-
Copy full SHA for 664ffc6 - Browse repository at this point
Copy the full SHA 664ffc6View commit details -
[TRANSFORMATIONS] Check if FROM types are different from a node's typ…
…e in ConvertPrecision (#27231) [TRANSFORMATIONS] Check if Select is 'relaxed' only if 0th input is not boolean in ConvertPrecision The ConvertPrecision transformation wraps Select node (its 0th input in particular) into RelaxedType to accept tensors with other element types than boolean. Add a check to perform the appearance of RelaxedType only if the 0th input is not boolean. Tickets: * CVS-155745 * CVS-155990 Signed-off-by: Andrii Staikov <andrii.staikov@intel.com> --------- Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2486a7f - Browse repository at this point
Copy the full SHA 2486a7fView commit details -
[GPU] KV-cache compression support (#27114)
### Details: This PR enables KV-cache compression support Currently, it supports only combinations of the following configurations: * Data types: INT8_SYM / INT8_ASYM * Modes: per-token (quantization of `num_heads * head_size` in a single group) / per-token-per-head (quantization of each `head_size` group for each head per token) ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 0d113d9 - Browse repository at this point
Copy the full SHA 0d113d9View commit details -
[PT FE] Support aten::lerp and aten::lerp_ (#27272)
### Details: - *Support `aten::lerp` and `aten::lerp_`* ### Tickets: - *CVS-156191*
Configuration menu - View commit details
-
Copy full SHA for 1baf261 - Browse repository at this point
Copy the full SHA 1baf261View commit details -
[STFT][Op][Spec] Update STFT-15 spec to describe 1D signal input supp…
Configuration menu - View commit details
-
Copy full SHA for 0c558f7 - Browse repository at this point
Copy the full SHA 0c558f7View commit details -
Configuration menu - View commit details
-
Copy full SHA for b2a9527 - Browse repository at this point
Copy the full SHA b2a9527View commit details -
Configuration menu - View commit details
-
Copy full SHA for 65313fc - Browse repository at this point
Copy the full SHA 65313fcView commit details -
[GHA] Use action_path in default smart ci config path (#27287)
For easier usage in 3rd-party repos Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for c158480 - Browse repository at this point
Copy the full SHA c158480View commit details
Commits on Oct 29, 2024
-
[TF FE] Deduce Switch-Merge predicate shape (#27277)
**Details:** It helps to convert some TF models out-of-the-box with static rank tensors that are required by plugins for inference. **Ticket:** 156204 --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for e07546d - Browse repository at this point
Copy the full SHA e07546dView commit details -
[SPEC][Op] Align SearchSorted specification with core (#27275)
### Details: - *Align SearchSorted tensor/attribute names with ones used in core* - *Minor improvements for descriptions* - *Fix SliceScatter missing opset number* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 744475b - Browse repository at this point
Copy the full SHA 744475bView commit details -
[CPU][OMP] Safe usage of threads num with buffers (#27237)
### Details: - *Function `parallel_get_max_threads()` may returns ether core number or threads number. That can affect buffers access which size depends on threads number.* - *...* ### Tickets: - *152606* --------- Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for dd7967c - Browse repository at this point
Copy the full SHA dd7967cView commit details -
[CPU] Drop redundant MemoryOutput nodes (#27189)
### Details: In direct ReadValue->Assign pairs the Assign node is practically useless as there are no other layers that might modify data in between. Therefore, it does make sense to remove corresponding MemoryOutput nodes to eliminate additional overheads on their processing. ### Tickets: - CVS-153035 - CVS-155112
Configuration menu - View commit details
-
Copy full SHA for c7d8e03 - Browse repository at this point
Copy the full SHA c7d8e03View commit details -
Configuration menu - View commit details
-
Copy full SHA for af18322 - Browse repository at this point
Copy the full SHA af18322View commit details -
Update android_x64.yml (#27257)
### Details: - Enabling test building by setting {ENABLE_TEST=ON} ### Tickets: - 149906 --------- Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 015de6d - Browse repository at this point
Copy the full SHA 015de6dView commit details -
[intel-npu] Bugfix for total allocable memory property (#27270)
### Details: - Bugfix in zero_device to return correct maximum allocable memory size in NPU_DEVICE_TOTAL_MEM_SIZE property. - For old drivers we return hardcoded 2GB value (compiler limitation) - For graph_ext 1.8 windows drivers we just convert KB to B - For graph_ext >1.9 drivers we return values from driver as is ### Tickets: - *EISW-143246*
Configuration menu - View commit details
-
Copy full SHA for a7ccc5e - Browse repository at this point
Copy the full SHA a7ccc5eView commit details -
[CPU] Disable parallel UpdateShapes/PrepairParams processing if there…
… are many sync nodes (#27280) ### Details: If there are too many sync nodes in a model, it's not beneficial to run UpdateShapes and PrepairParams stages in parallel as the parallel tasks spawning/synchronization overheads outweigh the performance gain of the parallel execution. As a quantitative characteristic that defines the boundary between parallel and sequential node processing strategy, we use the ratio between the total number of nodes and the number of synchronous nodes. ### Tickets: - CVS-153035 - CVS-155112
Configuration menu - View commit details
-
Copy full SHA for fc5f897 - Browse repository at this point
Copy the full SHA fc5f897View commit details -
[CPU] enable channel first format support for rank=3 Deconv to use am…
…x fp16 kernel (#27085) ### Details: - *enable channel first format support for rank=3 Deconv to use amx fp16 kernel to benefit model performance on GNR, e.g. hifigan* - *fix acl_convert UNKNOWN DataLayout accuracy issues* ### Tickets: - *153089*
Configuration menu - View commit details
-
Copy full SHA for cde0429 - Browse repository at this point
Copy the full SHA cde0429View commit details -
[CPU][ARM] Fix ARM tests failing because of overflow (#27074)
### Details: - Fixes ARM test overflow for Multiple Query SDP.
Configuration menu - View commit details
-
Copy full SHA for 583925c - Browse repository at this point
Copy the full SHA 583925cView commit details -
[TESTS] Disable lerp test for torch.export on older versions (#27302)
### Details: - *Disable `lerp_` test for `torch.export` on older versions of `torch`* ### Tickets: - *CVS-156278* Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 08c6672 - Browse repository at this point
Copy the full SHA 08c6672View commit details -
[CPU] Introduce LoRA macro operation (#27110)
### Details: To minimize the overheads on the LoRA subgraph operation processing (shape update, memory allocation, etc.) it does make sense to merge such subgraphs into a specific LoRA macro operation, which may exploit some LoRA properties to optimize performance. ### Tickets: - CVS-153035 - CVS-155112
Configuration menu - View commit details
-
Copy full SHA for 60e348b - Browse repository at this point
Copy the full SHA 60e348bView commit details -
[TF FE] Update tensorflow-text version and fix jax version for MacOS …
…x86 (#27295) **Details:** Update tensorflow-text version and fix jax version for MacOS x86 **Ticket:** 156277 --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3ced1c1 - Browse repository at this point
Copy the full SHA 3ced1c1View commit details -
Disabled regional compilation (#27289)
### Details: - Torch 2.5.0 enabled regional compilation by default which degrades the performance of openvino backend ### Tickets: - (https://jira.devtools.intel.com/browse/CVS-156251) --------- Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 669537a - Browse repository at this point
Copy the full SHA 669537aView commit details -
[def/transformations]: Fix for failing roblox model at ConvertPrecisi…
…on transformation (#27298) ### Details: - Fix for failing roblox model on ConvertPrecision transformation. ### Tickets: - CVS-156058 --------- Co-authored-by: Andrii Staikov <andrii.staikov@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9235543 - Browse repository at this point
Copy the full SHA 9235543View commit details -
[Wheel] return back JAX FE (#27309)
### Details: - Regression after #26610 ### Tickets: - CVS-156317
Configuration menu - View commit details
-
Copy full SHA for 99f3a91 - Browse repository at this point
Copy the full SHA 99f3a91View commit details -
[STFT][Op][Python] Fix STFT Python API to pass attribute (#27311)
### Details: - Fix STFT Python API to pass "transpose_frames" attribute ### Tickets: - 147160
Configuration menu - View commit details
-
Copy full SHA for fc105b0 - Browse repository at this point
Copy the full SHA fc105b0View commit details -
[GPU] Fix sdpa opt accuracy (#27262)
### Details: - Fix accuracy for sdpa_opt ### Tickets: - 154583
Configuration menu - View commit details
-
Copy full SHA for bd6cf01 - Browse repository at this point
Copy the full SHA bd6cf01View commit details -
Enable - disabling ORT optimizations flag in protopipe app (#27182)
### Details: - Enable - disabling ORT optimizations flag - in protopipe app Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 4d29e2e - Browse repository at this point
Copy the full SHA 4d29e2eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 874bf8a - Browse repository at this point
Copy the full SHA 874bf8aView commit details
Commits on Oct 30, 2024
-
Revert "[GPU] Fixes for hybrid quantization (#27127)" (#27308)
This reverts commit c21f572. Signed-off-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 95a6f18 - Browse repository at this point
Copy the full SHA 95a6f18View commit details -
Configuration menu - View commit details
-
Copy full SHA for 961b891 - Browse repository at this point
Copy the full SHA 961b891View commit details -
[GPU] Add per layer scaling for FC to fix accuracy issue regarding fp…
…16 overflow (#27291) ### Details: - Fix LLM accuracy issue due to fp16 overflow when using decompression_post_opt in fully_connected_gpu_bf_tiled_opt kernel - In the fc kernel, to optimize grouped scale, we calculate acc first as mad of activation (fp16) * weight (int4) first , and then apply scale value. This can cause accuracy issue when only multiply of activation and weight overflows. - In this case we can resolve the issue by applying scale down to the activation. - Implement per layer scaling for FCs ### Tickets: - 154583 --------- Signed-off-by: Andrew Park <andrew.park@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f12f086 - Browse repository at this point
Copy the full SHA f12f086View commit details -
[CPU][OMP] Handle exception outside parallel region (#27303)
### Details: - *Handle exception inside OMP threads to avoid immediate program interruption.* ### Tickets: - *152606* Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9036b59 - Browse repository at this point
Copy the full SHA 9036b59View commit details -
[GPU] model cache fix from kv cache compression (#27323)
### Details: - model cache was not working because of load/save mismatch
Configuration menu - View commit details
-
Copy full SHA for 8da8a30 - Browse repository at this point
Copy the full SHA 8da8a30View commit details -
[intel-npu] max memalloc quickfix for grext 1.8 windows drivers (#27317)
### Details: - another quickfix for maximum memory allocation property, to enable UD44 windows drivers too - addition to #27270 ### Tickets: - *EISW-143246*
Configuration menu - View commit details
-
Copy full SHA for 70e214d - Browse repository at this point
Copy the full SHA 70e214dView commit details -
[DOCS] Fixing formatting in the STFT article. (#27312)
Fixing formatting issues in the `Short Time Fourier Transformation for real-valued input` article.
Configuration menu - View commit details
-
Copy full SHA for 9263641 - Browse repository at this point
Copy the full SHA 9263641View commit details -
[PT FE] Unify conversion pipeline for ExportedProgram from memory and…
… disk (#27324) **Details:** Before the fix, conversions of ExportedProgram from memory and disk use different decomposition sets **Tickets:** TBD Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 22c6740 - Browse repository at this point
Copy the full SHA 22c6740View commit details -
[GPU] Disable OneDNN for unknown arch via dpas flag faking (#27326)
### Details: - This patch enforces dpas availability flag to false when HW architecture is unknown to onednn to fallback to OCL kernels which are supposed to be more generic and more forward compatible. - Also, added an architecture check in each onednn-based impl if in the future we'll stop relying on `supports_immad` flag when decide whether to use onednn or not. Signed-off-by: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 11cf409 - Browse repository at this point
Copy the full SHA 11cf409View commit details -
add support aten::__ior__ (#27315)
### Details: - *add support `aten::__ior__`, `aten::__iand__`, `aten::__ixor__`* ### Tickets: - *CVS-156301*
Configuration menu - View commit details
-
Copy full SHA for cb292c7 - Browse repository at this point
Copy the full SHA cb292c7View commit details -
[GPU] Init tensor.data when allocating inputs for string type (#27269)
### Details: - In case the element type is string produces the segmentation fault when input data is an empty string, unless the each element of tensor.data is initialized. ### Tickets: - 148921
Configuration menu - View commit details
-
Copy full SHA for a7ff891 - Browse repository at this point
Copy the full SHA a7ff891View commit details -
[TF FE] Stabilize tests for UnsortedSegmentSum operation on all platf…
…orms (#27325) **Details:** Stabilize tests for UnsortedSegmentSum operation on all platforms **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2441dcd - Browse repository at this point
Copy the full SHA 2441dcdView commit details -
Docs Added searching by new coveo Category (#27335)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 118efc8 - Browse repository at this point
Copy the full SHA 118efc8View commit details -
[GPU] Fix cache mode and weights path interaction (#27328)
### Details: - Currently ov::CacheMode::OPTIMIZE_SIZE behaves like ov::CacheMode::OPTIMIZE_SPEED if weights_path is provided. This change fixes that. - Additionally, after this change if cache is saved with OPTIMIZE_SIZE and the user tries to load with OPTIMIZE_SPEED (or vice versa), import_model() will fail and the workload will behave like during the first launch, according to the cache mode set by the user. - This change also tightens the weights_path value validation - only files with ".bin" extension will be accepted. However, if the user provides the path to the wrong bin file, the execution will still fail - there's no way to validate if the bin file is correct without storing information about it in the cache. ### Tickets: - 156265 --------- Co-authored-by: Tomasz Krupa <tomasz.krupa@intel.com>
Configuration menu - View commit details
-
Copy full SHA for a5a0941 - Browse repository at this point
Copy the full SHA a5a0941View commit details -
Docs Unhide columns in datatableJs (#27338)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 37f5dd3 - Browse repository at this point
Copy the full SHA 37f5dd3View commit details -
[DOCS] Fix submodule update for building OV on Windows (#26549)
- Add missing --recursive args for submodule update - Referenece guide for linux: https://github.com/openvinotoolkit/openvino/blob/6dc3f5538057caed5dd2eda0797aec445b6105bf/docs/dev/build_linux.md?plain=1#L23
Configuration menu - View commit details
-
Copy full SHA for b60449e - Browse repository at this point
Copy the full SHA b60449eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 967a730 - Browse repository at this point
Copy the full SHA 967a730View commit details -
squeeze v15 implementation (#26995)
### Details: - Add v15::Squeeze class with support dynamic rank result based on v0::Squeeze ### Tickets: - [*154023*](https://jira.devtools.intel.com/browse/CVS-154023)
Configuration menu - View commit details
-
Copy full SHA for 6e35049 - Browse repository at this point
Copy the full SHA 6e35049View commit details -
[PT FE] Support torch 2.5.1 (#27334)
### Details: - *Support torch 2.5.1* - *Update test requirements* ### Tickets: - *ticket-id* Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1ec99ee - Browse repository at this point
Copy the full SHA 1ec99eeView commit details -
[ONNX] Added QuickGelu from com.microsoft domain (#27238)
### Details: - Microsoft Contrib Operator "QuickGelu" for ONNX RT ### Tickets: - CVS-152783 --------- Co-authored-by: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
Configuration menu - View commit details
-
Copy full SHA for a6eb535 - Browse repository at this point
Copy the full SHA a6eb535View commit details -
Configuration menu - View commit details
-
Copy full SHA for e44ea54 - Browse repository at this point
Copy the full SHA e44ea54View commit details
Commits on Oct 31, 2024
-
[GPU] Support int8 dyn-quan FC (#27027)
### Details: - Support FC dynamic quantize for 8Bit Asym model - Enable SLM for 8bit weight ### Tickets: - CVS-152990 --------- Signed-off-by: Min, Byung-il <byungil.min@intel.com> Signed-off-by: Min, Byungil <byungil.min@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b5a5953 - Browse repository at this point
Copy the full SHA b5a5953View commit details -
[GPU] Fix per-token dynamic quantization (#27332)
### Details: - Allow the DynamicQuantizeKernelOpt kernel to be selected with the default scales order - Relax DynamicQuantizeKernelRef kernel validation function
Configuration menu - View commit details
-
Copy full SHA for 9ec63be - Browse repository at this point
Copy the full SHA 9ec63beView commit details -
Add /MT[d] to CMAKE_LANG_FLAGS_CONFIG_INIT (#27173)
### Details: Add /MT[d] to CMAKE_LANG_FLAGS_CONFIG_INIT to avoid the missing of /O2 /Ob2 /DNDEBUG flags in CMAKE_LANG_FLAGS_CONFIG ### Tickets: - *152927* Signed-off-by: Kang Wenjing <wenjing.kang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f60b9c4 - Browse repository at this point
Copy the full SHA f60b9c4View commit details -
[GPU] Add subsequent reshapes optimization and dynamic paddings suppo…
…rt for RoPE and PagedAttention (#27329) ### Details: - Added subsequent reshapes optimization - Added dynamic paddings support for RoPE and PagedAttention ### Tickets: - [CVS-156124](https://jira.devtools.intel.com/browse/CVS-156124)
Configuration menu - View commit details
-
Copy full SHA for 689e043 - Browse repository at this point
Copy the full SHA 689e043View commit details -
[GPU] Handling the case where get_state was called before set_state (#…
…27276) ### Tickets: - *[156193](https://jira.devtools.intel.com/browse/CVS-156193)*
Configuration menu - View commit details
-
Copy full SHA for 2e87aad - Browse repository at this point
Copy the full SHA 2e87aadView commit details -
[GPU] Use onednn impl for dynamic gemm (#27212)
### Details: - *Performance improvement for LoRA*
Configuration menu - View commit details
-
Copy full SHA for a6a113c - Browse repository at this point
Copy the full SHA a6a113cView commit details -
Bump paddlepaddle from 2.6.0 to 2.6.2 in /src/bindings/python (#26966)
Bumps [paddlepaddle](https://github.com/paddlepaddle/paddle) from 2.6.0 to 2.6.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/paddlepaddle/paddle/releases">paddlepaddle's releases</a>.</em></p> <blockquote> <h2>PaddlePaddle 2.6.1 Release Note</h2> <h1>发版说明</h1> <p>此版本在新功能方面,引入了对Fake GroupWise Quant的支持,有助于用户更好地进行模型量化。同时新增了图神经网络训练引擎PGLBox,支持超大规模图模型GPU多机多卡高效训练。此外,增加了对自定义设备的支持,进一步扩展PaddlePaddle的功能范围。在bug方面,解决了一些核心功能、数据加载以及网络通信等方面的问题。修复了多个安全问题,包括一些潜在的安全漏洞,进一步提高框架代码安全性,并更新了安全公告。</p> <h2>新特性</h2> <ul> <li><strong>支持Fake GroupWise量化(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61900">#61900</a>)</strong>:新增对一种量化方法的支持,可以提高模型的性能效率。</li> <li><strong>支持图神经网络GPU训练(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60495">#60495</a>,<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62111">#62111</a>)</strong>:新增图神经网络训练引擎PGLBox,支持超大规模图模型GPU多机多卡高效训练。</li> <li><strong>其他改进</strong>:支持tile op int8模式推理,并添加vlog语句 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60261">#60261</a>),repeat_interleave支持bfloat16数据类型的Tensor输入 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61854">#61854</a>),自定义设备支持动态图模式的c_embedding算子 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60774">#60774</a>),在CINN(自定义中间网络)框架中,将IntrinsicOps添加到<code>ir_codes_collector</code>中。</li> </ul> <h2>Bug修复</h2> <ul> <li><strong>修复权重量化内核错误(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60184">#60184</a>)</strong>:解决了在权重量化内核中当<code>n</code>不能被64整除时的问题。</li> <li><strong>修复量化感知测试问题(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61211">#61211</a>)</strong>:修复了量化感知训练(QAT)测试中的问题,以确保其正常运行。</li> <li><strong>修复Paddle-TRT集成问题(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61806">#61806</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61605">#61605</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61966">#61966</a>)</strong>:对Paddle-TRT集成进行了多项修复,包括缓存键值(KV)量化和单元测试失败问题。</li> <li><strong>禁用LLM_INT8 UT(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62282">#62282</a>)</strong>:禁用了大型语言模型(LLM)INT8精度的单元测试,以避免不必要的运行时。</li> <li><strong>修复test_benchmark单测编译失败问题(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61427">#61427</a>)</strong>:修复了test_benchmark单测编译失败的问题<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60092">#60092</a>。</li> <li><strong>修复工具包的数据加载器(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61867">#61867</a>)</strong>:对工具包的数据加载器进行了必要的更正。</li> <li><strong>修复put_along_axis系列问题(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62065">#62065</a>)</strong>:对reduce参数新增支持min/max/mean三种可选值,修复了reduce=add/mul下的反向梯度计算Bug, 修复了reduce=mul下的GPU前向计算Bug,修复了size过大时的前向计算Bug。</li> <li><strong>修复Windows平台下的编译Bug(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60308">#60308</a>)</strong>:修复windows平台下的编译找不到common库的bug。</li> <li><strong>修复OpenSSL-CPU编译错误(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62079">#62079</a>)</strong>:修复cpu-openblas编译场景中未正确链接 Python 库导致的编译bug。</li> </ul> <h2>安全修复</h2> <ul> <li><strong>修复安全问题(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61161">#61161</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61294">#61294</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61032">#61032</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61285">#61285</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61162">#61162</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61389">#61389</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61356">#61356</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61827">#61827</a>)</strong>:修复了涉及绘图功能、解压缩和命令执行的多个安全问题,以确保框架的安全性和完整性。</li> <li><strong>禁用特定测试(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60173">#60173</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60662">#60662</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60786">#60786</a>)</strong>:禁用了某些未通过或不适用于特定配置或版本的测试。</li> <li><strong>修复框架不同组件Bug(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61631">#61631</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/62117">#62117</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60840">#60840</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/62104">#62104</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60217">#60217</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60930">#60930</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61380">#61380</a>)</strong>:在框架的不同组件中修复了各种Bug。</li> <li><strong>修复自定义设备功能(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60616">#60616</a>)</strong>:打开自定义设备中生成器偏移量的编译控制。</li> <li><strong>内存和分配检查(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60208">#60208</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60545">#60545</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/61847">#61847</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/62111">#62111</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/62057">#62057</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/62278">#62278</a>)</strong>:实施了与内存分配和管理相关的检查和修复,以防止崩溃并提高稳定性。</li> </ul> <h2>文档</h2> <ul> <li><strong>文档风格改进(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/61688">#61688</a>)</strong>:改进了文档的样式和格式。</li> <li><strong>安全公告更新(<a href="https://redirect.github.com/paddlepaddle/paddle/issues/60532">#60532</a>, <a href="https://redirect.github.com/paddlepaddle/paddle/issues/60649">#60649</a>)</strong>:更新了2023年的安全公告,以通知用户潜在的安全问题。</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/8ce0de584c570589117e403322f3d1a0de6554e5"><code>8ce0de5</code></a> fix einsum issue (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/67588">#67588</a>) (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/67825">#67825</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/d16d420ad31f496fa461da592e58afe79204137d"><code>d16d420</code></a> fix numpy2.0/2.1 bug in release/2.6 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/67958">#67958</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/64c69370083e0adfb830a509aea31c6bc86ec6e2"><code>64c6937</code></a> [cherry-pick] Fix numpy2.1 bug in py3.10 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/67866">#67866</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/94c6682a4ba59081c2f01f760d84ca61574fbba5"><code>94c6682</code></a> fix to_tensor bug (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/67795">#67795</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/6267a2bd93267396ca9209b5a56d7bf65c10baf3"><code>6267a2b</code></a> [XPU] Support int31 weight dynamic quantization for fc and conv2d (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/59981">#59981</a>) (#...</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/736a253dec08c4f4a3eec0fa1ee4ad8f052a4d8c"><code>736a253</code></a> [XPU] Fix L3 autotune (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/66323">#66323</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/131999233ef997fc8d3f24b27830925b78cf17aa"><code>1319992</code></a> fix rpc_sync and rpc_async doc;test=develop (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/64107">#64107</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/90138318312fbb60b0bdce8b0f4fb317879fe62e"><code>9013831</code></a> [Dy2St][2.6] Disable <code>test_sentiment</code> on release/2.6 (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/63197">#63197</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/89a60d773893640b7cec91d4857d634a61b02304"><code>89a60d7</code></a> Revert "fix security (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62626">#62626</a>) (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62683">#62683</a>)" (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62890">#62890</a>)</li> <li><a href="https://github.com/PaddlePaddle/Paddle/commit/0348f3f9ab802ab8456cf8ee0fbac290af089088"><code>0348f3f</code></a> Enhance several unit tests (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62477">#62477</a>) (<a href="https://redirect.github.com/paddlepaddle/paddle/issues/62776">#62776</a>)</li> <li>Additional commits viewable in <a href="https://github.com/paddlepaddle/paddle/compare/v2.6.0...v2.6.2">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=paddlepaddle&package-manager=pip&previous-version=2.6.0&new-version=2.6.2)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 9f6826a - Browse repository at this point
Copy the full SHA 9f6826aView commit details -
[PyOV] allow constant accept keyword args (#27346)
### Details: - using of singledispatch breaks the scenario where a user pass keywords arguments only ### Tickets: - CVS-153553
Configuration menu - View commit details
-
Copy full SHA for 2f78f6f - Browse repository at this point
Copy the full SHA 2f78f6fView commit details -
NPUW: Eliminate unnecessary kvcache tensors copy (#27347)
### Details: - We mistakenly copy input parameters when we shouldn't - Yet another `||` -> `&&` change, hopefully less destructive this time ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 66b1467 - Browse repository at this point
Copy the full SHA 66b1467View commit details -
benchmark_app/cpp: report an error if no files were found. (#26663)
Python version already reports an error in that case. benchmark_app is the only user of `readInputFilesArguments()`. It could make sense earlier to emit the warning instead of the error because other samples. Ticket 152614
Configuration menu - View commit details
-
Copy full SHA for 44b86a8 - Browse repository at this point
Copy the full SHA 44b86a8View commit details -
[Transformations] Add Squeeze-15 downgrade transformation (#27286)
### Details: - *Add Squeeze-15 downgrade transformation to Squeeze-0 for compatible attribute* - *...* ### Tickets: - *CVS-154027* ### PR requires [PR-26995](#26995) to be merged --------- Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 86083e0 - Browse repository at this point
Copy the full SHA 86083e0View commit details -
[Snippets][CPU][Tests] Added tests for dynamic BF16/INT8 MHA (#27169)
### Details: - *Added more tests for the validation of INT8/BF16 MHA in CPU Plugin* - *Split the large "mha.cpp" file into the several small files with the same test semantic (comment #26547 (comment) ### Tickets: - *N/A*
Configuration menu - View commit details
-
Copy full SHA for c685d44 - Browse repository at this point
Copy the full SHA c685d44View commit details -
Update CMAKE_LANG_FLAGS_CONFIG_INIT appending in toolchain to avoid f…
…lag repetition (#27352) ### Details: -Currently, when using this toolchain and print the following flags in [CMakeLists](https://github.com/openvinotoolkit/openvino/blob/master/CMakeLists.txt) ``` CMAKE_CXX_FLAGS_RELEASE in OV CMakeLists.txt::: /MT /MT /O2 /Ob2 /DNDEBUG /Zi /FS /Zf /ZH:SHA_256 /guard:cf /Qspectre CMAKE_C_FLAGS_RELEASE in OV CMakeLists.txt::: /MT /MT /O2 /Ob2 /DNDEBUG /Zi /FS /Zf /ZH:SHA_256 /guard:cf /Qspectre CMAKE_CXX_FLAGS_RELEASE_INIT in OV CMakeLists.txt::: /MT /MT /O2 /Ob2 /DNDEBUG CMAKE_C_FLAGS_RELEASE_INIT in OV CMakeLists.txt::: /MT /MT /O2 /Ob2 /DNDEBUG ``` So there is repetition of `/MT` in flags. The change in this PR will fix this problem. The flags will be: ``` CMAKE_CXX_FLAGS_RELEASE in OV CMakeLists.txt::: /MT /O2 /Ob2 /DNDEBUG /Zi /FS /Zf /ZH:SHA_256 /guard:cf /Qspectre CMAKE_C_FLAGS_RELEASE in OV CMakeLists.txt::: /MT /O2 /Ob2 /DNDEBUG /Zi /FS /Zf /ZH:SHA_256 /guard:cf /Qspectre CMAKE_CXX_FLAGS_RELEASE_INIT in OV CMakeLists.txt::: /MT /O2 /Ob2 /DNDEBUG CMAKE_C_FLAGS_RELEASE_INIT in OV CMakeLists.txt::: /MT /O2 /Ob2 /DNDEBUG ``` ### Tickets: - *152927* Signed-off-by: Kang Wenjing <wenjing.kang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f2640a2 - Browse repository at this point
Copy the full SHA f2640a2View commit details -
Add support for shape and data_shape parameters (#27314)
### Details: - Move helper function for reshaping to `npu_tools_utils` - Introduce `shape` and `data_shape` params ### Tickets: - E144161 --------- Signed-off-by: Skrebkov, Artemy <artemy.skrebkov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 272843d - Browse repository at this point
Copy the full SHA 272843dView commit details -
Configuration menu - View commit details
-
Copy full SHA for c902a01 - Browse repository at this point
Copy the full SHA c902a01View commit details -
[PyOV] Extend Python API with
Squeeze-15
(#27281)### Details: - This PR includes commits from #26995 ### Tickets: - CVS-154024 --------- Signed-off-by: p-wysocki <przemyslaw.wysocki@intel.com> Co-authored-by: Michal Barnas <michal.barnas@intel.com> Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for a0b73e0 - Browse repository at this point
Copy the full SHA a0b73e0View commit details -
[ONNX] Update DequantizeLinear21 converter (#27351)
### Details: Aligned with the canonical form of the dequantization subgraph. Reshape op has been moved up right after the Constant, it will be const folded in MOC, this is ok, Reshape const folding doesn't copy a constant, just copies a pointer. And ConvertLike were replaced with Convert. Perhaps that's a pretty rough change and we need to add a check here that the scale is a contant. And in that case use Convert instead of ConvertLike, if scale is not a constant, maybe we should leave ConvertLike. ### Tickets: - *https://jira.devtools.intel.com/browse/CVS-156329*
Configuration menu - View commit details
-
Copy full SHA for b9a94c3 - Browse repository at this point
Copy the full SHA b9a94c3View commit details
Commits on Nov 1, 2024
-
[TF FE] Run string ops tests on ARM (#27367)
**Details:** Since openvino-tokenizers is build for ARM in the precommit, we are ready to switch on String ops tests **Ticket:** TBD Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for a488aec - Browse repository at this point
Copy the full SHA a488aecView commit details -
[ONNX] Disabled constant folding for Subtract branch of DequantizeLin…
…ear-21 (#27359) ### Details: - Disabled constant folding for Subtract branch of DequantizeLinear-21 ### Tickets: - 156329
Configuration menu - View commit details
-
Copy full SHA for 5833781 - Browse repository at this point
Copy the full SHA 5833781View commit details -
Broadcast: symbol propagation (#27357)
### Details: - *Improves symbol propagation in LLMs and allows for better ShapeOf optimization* Signed-off-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com>
Configuration menu - View commit details
-
Copy full SHA for af389b4 - Browse repository at this point
Copy the full SHA af389b4View commit details -
[NPU] Create compiler adapter class (#27006)
### Details: - *Create a new CompilerAdapter interface that hides different implementations of CIP and CID* - *iCompiler remains an interface only for CIP. This keeps CIP (developed in another repository) decoupled from L0* - we still use NetworkMetadata in the plugin flow, which needs to be decided later if is still needed or if it can be removed - *Graph object is created by compiler_adapter* - *Backend doesn't create/initialize graph any longer* - *Moving common objects for backend and compiler_adapter to utils/zero/* - *Destroy blob on the import path after we load the weights into the NPU memory* - *Create a new property to postpone weights loading until the creation of the first inference request, by default is performed right after the model is compiled - NPU_DEFER_WEIGHTS_LOAD* A short description of the new format: ![Screenshot 2024-10-30 151129](https://github.com/user-attachments/assets/89f86c36-f3e8-4906-8394-7cd0ae5617a2) ### Tickets: - *CVS-153081* --------- Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for caa1e6a - Browse repository at this point
Copy the full SHA caa1e6aView commit details -
[ONNX] Updated a required version of ONNXRuntime for layer tests (#27368
Configuration menu - View commit details
-
Copy full SHA for 49e99f2 - Browse repository at this point
Copy the full SHA 49e99f2View commit details -
[NPU] Add zero_api when zero functions are used (#27373)
### Details: - *Add zero_api when zero functions are used* ### Tickets: - *ticket-id* Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1104581 - Browse repository at this point
Copy the full SHA 1104581View commit details
Commits on Nov 4, 2024
-
Add squeeze v15 op spec (#26989)
### Details: - Add squeeze v15 op spec ### Tickets: - [*154021*](https://jira.devtools.intel.com/browse/CVS-154021)
Configuration menu - View commit details
-
Copy full SHA for 4d8ff86 - Browse repository at this point
Copy the full SHA 4d8ff86View commit details -
Configuration menu - View commit details
-
Copy full SHA for 56d8fb5 - Browse repository at this point
Copy the full SHA 56d8fb5View commit details -
Configuration menu - View commit details
-
Copy full SHA for b067ae1 - Browse repository at this point
Copy the full SHA b067ae1View commit details -
[DOCS] Updating system requirements for OpenVINO (#27233)
Moving info on system requirements for distributions of OpenVINO to one article. --------- Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Configuration menu - View commit details
-
Copy full SHA for ef738c7 - Browse repository at this point
Copy the full SHA ef738c7View commit details -
[CI] [GHA] Use an internal image for
docker buildx
setup (#27380)Should eliminate the problem of getting images from public Docker Hub: https://github.com/openvinotoolkit/openvino/actions/runs/11652494488/job/32456237021?pr=27374 Ticket: 156671
Configuration menu - View commit details
-
Copy full SHA for fc391e4 - Browse repository at this point
Copy the full SHA fc391e4View commit details -
[GPU] Enable bf16 state conversions (#27361)
### Details: - Added support for bf16 LoRA adapters - Minor debug code cleanup ### Tickets: - *[153069](https://jira.devtools.intel.com/browse/CVS-153069)*
Configuration menu - View commit details
-
Copy full SHA for 0c84af0 - Browse repository at this point
Copy the full SHA 0c84af0View commit details -
Configuration menu - View commit details
-
Copy full SHA for 7800a03 - Browse repository at this point
Copy the full SHA 7800a03View commit details -
[Fix][STFT] OPENVINO_OP macro for STFT with opset15 (#27386)
### Details: - Fix OPENVINO_OP macro for STFT with opset15 (without that it is registered and serialized with version="extension" by default, and can't be deserialized) - It follows all of the other ops OPENVINO_OP macro, the "opset15" has been missed for STFT Example: https://github.com/openvinotoolkit/openvino/blob/4d8ff86bd2e853b84a28acd2ece1836d28523f9e/src/core/include/openvino/op/slice_scatter.hpp#L17 ### Tickets: - 156667
Configuration menu - View commit details
-
Copy full SHA for d69ac00 - Browse repository at this point
Copy the full SHA d69ac00View commit details
Commits on Nov 5, 2024
-
[GPU] Fix unexpected runtime skip permute (#27362)
### Details: - Fix error found in mixtral model for shape [8, 2, 8] and permute order [2, 1, 0], which was optimized out unexpectedly - Reimplemented skipping algorithm ### Tickets: - 154591
Configuration menu - View commit details
-
Copy full SHA for 71f9ba4 - Browse repository at this point
Copy the full SHA 71f9ba4View commit details -
[GPU] Remove unused crop layer. (#27363)
### Details: - *Remove unused crop layers created by VariadicSplit.* ### Tickets: - *153542*
Configuration menu - View commit details
-
Copy full SHA for 9eab491 - Browse repository at this point
Copy the full SHA 9eab491View commit details -
[GPU] Fix issue for Flux.1 int4 WC model memory overuse. (#27376)
Flux.1 text_encoder_2_int4 model has unusual WC pattern. (Needs extra multiply) Add this in the target matcher. ### Tickets: - *154194* --------- Signed-off-by: hyunback <hyunback.kim@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b8c5bd8 - Browse repository at this point
Copy the full SHA b8c5bd8View commit details -
[GPU] Model cache segfault fix (#27377)
### Details: - Primitives can be opt-out. In that case, it does not have kernel data. ### Tickets: - 156592
Configuration menu - View commit details
-
Copy full SHA for cde4e97 - Browse repository at this point
Copy the full SHA cde4e97View commit details -
[OV JS] Simplify run js samples (#27206)
### Details: - Add script to fetch static - Update run instructions - Remove logic of downloading model from notebooks - Put image manipulation logic in one file - Refactor notebooks structure - Remove opencv-wasm dependency ### Tickets: - 154015
Configuration menu - View commit details
-
Copy full SHA for a31640b - Browse repository at this point
Copy the full SHA a31640bView commit details -
[TF FE] Provide better support for TopKV2 and stabilize test (#27374)
**Details:** Provide better validation for TopKV2 and stabilize test **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 892eea4 - Browse repository at this point
Copy the full SHA 892eea4View commit details -
[Transformations][CPU] LoraFusion: convert on states support (#27340)
### Details: - *This PR extends LoraFusion transformation: convert on states support is added* - *The corresponding transformation tests are extended* - *Fixed a critical bug in the memory reuse between the LoRA subgraph and the main CPU graph* ### Tickets: - CVS-155112 - CVS-153035 --------- Co-authored-by: Maksim Kutakov <maksim.kutakov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6878482 - Browse repository at this point
Copy the full SHA 6878482View commit details -
Configuration menu - View commit details
-
Copy full SHA for 7c73c50 - Browse repository at this point
Copy the full SHA 7c73c50View commit details -
[DOCS] Updating notebooks (#27401)
Updating the `Interactive Tutorials` section.
Configuration menu - View commit details
-
Copy full SHA for c2e42fa - Browse repository at this point
Copy the full SHA c2e42faView commit details -
Co-authored-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 84e6837 - Browse repository at this point
Copy the full SHA 84e6837View commit details -
Use pyOv tests requirements (#27252)
### Details: - move dependency for torchvision preprocessing to the part where it tests - update numpy upperbound for testing PyOV & numpy 2.1 ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for eb80f9b - Browse repository at this point
Copy the full SHA eb80f9bView commit details -
[c-api] PPP add pad step (#27353)
### Details: - Add image padding support in PrePostProcessor for C API ### Continuation of PR: - #26730 ### Tickets: - CVS-152252 --------- Co-authored-by: panhaiqi <haiqi.pan@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 7171a7d - Browse repository at this point
Copy the full SHA 7171a7dView commit details -
[core] Remove LSTM sequence v0 (#27330)
### Details: - Remove LSTM Sequence v0 operator ### Tickets: - CVS-156182 --------- Signed-off-by: Pawel Raasz <pawel.raasz@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 59ddd74 - Browse repository at this point
Copy the full SHA 59ddd74View commit details -
[core] Remove legacy tensor name (#27307)
### Details: - Remove legacy name from tensor descriptor ### Related PR: - #26855 ### Tickets: - CVS-156182 --------- Signed-off-by: Pawel Raasz <pawel.raasz@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 2725b16 - Browse repository at this point
Copy the full SHA 2725b16View commit details -
[GHA] Set commit action versions (#27384)
### Details: - Use commit action versions as security requirement ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for fd2d6dc - Browse repository at this point
Copy the full SHA fd2d6dcView commit details -
[GHA] Switch coverity pipeline to internal docker image (#27385)
### Details: - Moved pipeline to ubuntu 20.04 image - Enabled sccache - ### Tickets: -156658
Configuration menu - View commit details
-
Copy full SHA for 7daf800 - Browse repository at this point
Copy the full SHA 7daf800View commit details -
[TF FE] Check OV and FW outputs shapes and types in layer tests (#27375)
**Details:** Check OV and FW outputs shapes and types in layer tests **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 0a3f439 - Browse repository at this point
Copy the full SHA 0a3f439View commit details -
[core] Remove deprecated element Type ctor (#27333)
### Details: - Removed deprecated and not used element Type constructor ### Tickets: - CVS-156179
Configuration menu - View commit details
-
Copy full SHA for c81a17f - Browse repository at this point
Copy the full SHA c81a17fView commit details -
[docs] Update LSTM sequence specification (version update) (#27355)
### Details: - Align LSTM sequence version in specification, after LSTM sequence v0 removal from OV opset. ### Blocked by: - #27330 ### Tickets: - CVS-156182
Configuration menu - View commit details
-
Copy full SHA for 41b2093 - Browse repository at this point
Copy the full SHA 41b2093View commit details -
[GPU] clean oneDNN cache by release memory method (#27403)
### Details: - Partial fix for https://jira.devtools.intel.com/browse/CVS-156022 - explicit call for release memory is required ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 7cf2bbb - Browse repository at this point
Copy the full SHA 7cf2bbbView commit details -
Bump OV version 2025.0 (#27412)
Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 1221a97 - Browse repository at this point
Copy the full SHA 1221a97View commit details -
[core] Remove deprecated members of Concat operator (#27339)
### Details: - Remove deprecated members of Concat operator: * get_concatenation_axis * set_concatenation_axis ### Tickets: - CVS-156181
Configuration menu - View commit details
-
Copy full SHA for 9204a20 - Browse repository at this point
Copy the full SHA 9204a20View commit details
Commits on Nov 6, 2024
-
[GPU] Disable crop fusing (#27417)
### Details: - *Disable crop fusing that was enabled in the #26951 ### Tickets: - *[156367](https://jira.devtools.intel.com/browse/CVS-156367)*
Configuration menu - View commit details
-
Copy full SHA for 7666e39 - Browse repository at this point
Copy the full SHA 7666e39View commit details -
[GHA] Changed android runner (#27414)
### Details: - Increased RAM ### Tickets: - *156361* --------- Co-authored-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 8a3277f - Browse repository at this point
Copy the full SHA 8a3277fView commit details -
[PyOV] Test for export-import via file (#27320)
### Details: - add a test where exported model saved to file and then imported from file - fix a problem with `inc_ref` and `dec_ref` when python callbacks are passed ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for cd15be9 - Browse repository at this point
Copy the full SHA cd15be9View commit details -
Bump codecov/codecov-action from 4.5.0 to 4.6.0 (#26882)
Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 4.5.0 to 4.6.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/codecov/codecov-action/releases">codecov/codecov-action's releases</a>.</em></p> <blockquote> <h2>v4.6.0</h2> <h2>What's Changed</h2> <ul> <li>build(deps): bump github/codeql-action from 3.25.8 to 3.25.10 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1481">codecov/codecov-action#1481</a></li> <li>build(deps): bump actions/checkout from 4.1.6 to 4.1.7 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1480">codecov/codecov-action#1480</a></li> <li>build(deps-dev): bump ts-jest from 29.1.4 to 29.1.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1479">codecov/codecov-action#1479</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.13.0 to 7.13.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1485">codecov/codecov-action#1485</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/eslint-plugin</code> from 7.13.0 to 7.13.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1484">codecov/codecov-action#1484</a></li> <li>build(deps-dev): bump typescript from 5.4.5 to 5.5.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1490">codecov/codecov-action#1490</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.13.1 to 7.14.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1493">codecov/codecov-action#1493</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/eslint-plugin</code> from 7.13.1 to 7.14.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1492">codecov/codecov-action#1492</a></li> <li>build(deps): bump github/codeql-action from 3.25.10 to 3.25.11 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1496">codecov/codecov-action#1496</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/eslint-plugin</code> from 7.14.1 to 7.15.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1501">codecov/codecov-action#1501</a></li> <li>build(deps-dev): bump typescript from 5.5.2 to 5.5.3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1500">codecov/codecov-action#1500</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.14.1 to 7.15.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1499">codecov/codecov-action#1499</a></li> <li>build(deps): bump actions/upload-artifact from 4.3.3 to 4.3.4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1502">codecov/codecov-action#1502</a></li> <li>build(deps-dev): bump ts-jest from 29.1.5 to 29.2.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1504">codecov/codecov-action#1504</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/eslint-plugin</code> from 7.15.0 to 7.16.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1503">codecov/codecov-action#1503</a></li> <li>build(deps-dev): bump ts-jest from 29.2.0 to 29.2.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1507">codecov/codecov-action#1507</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.15.0 to 7.16.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1505">codecov/codecov-action#1505</a></li> <li>build(deps): bump github/codeql-action from 3.25.11 to 3.25.12 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1509">codecov/codecov-action#1509</a></li> <li>chore(ci): restrict scorecards to codecov/codecov-action by <a href="https://github.com/thomasrockhu-codecov"><code>@thomasrockhu-codecov</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1512">codecov/codecov-action#1512</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/eslint-plugin</code> from 7.16.0 to 7.16.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1514">codecov/codecov-action#1514</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.16.0 to 7.16.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1513">codecov/codecov-action#1513</a></li> <li>test: <code>versionInfo</code> by <a href="https://github.com/marcobiedermann"><code>@marcobiedermann</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1407">codecov/codecov-action#1407</a></li> <li>build(deps-dev): bump ts-jest from 29.2.2 to 29.2.3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1515">codecov/codecov-action#1515</a></li> <li>build(deps): bump github/codeql-action from 3.25.12 to 3.25.13 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1516">codecov/codecov-action#1516</a></li> <li>build(deps-dev): bump typescript from 5.5.3 to 5.5.4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1521">codecov/codecov-action#1521</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.16.1 to 7.17.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1520">codecov/codecov-action#1520</a></li> <li>build(deps-dev): bump <code>@typescript-eslint/parser</code> from 7.17.0 to 7.18.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1528">codecov/codecov-action#1528</a></li> <li>build(deps): bump github/codeql-action from 3.25.13 to 3.25.15 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1526">codecov/codecov-action#1526</a></li> <li>build(deps): bump ossf/scorecard-action from 2.3.3 to 2.4.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1525">codecov/codecov-action#1525</a></li> <li>build(deps-dev): bump ts-jest from 29.2.3 to 29.2.4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1532">codecov/codecov-action#1532</a></li> <li>build(deps): bump actions/upload-artifact from 4.3.4 to 4.3.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1534">codecov/codecov-action#1534</a></li> <li>build(deps): bump github/codeql-action from 3.25.15 to 3.26.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1542">codecov/codecov-action#1542</a></li> <li>build(deps): bump actions/upload-artifact from 4.3.5 to 4.3.6 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1541">codecov/codecov-action#1541</a></li> <li>ref: Tidy up types and remove string coercion by <a href="https://github.com/nicholas-codecov"><code>@nicholas-codecov</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1536">codecov/codecov-action#1536</a></li> <li>build(deps-dev): bump <code>@octokit/webhooks-types</code> from 3.77.1 to 7.5.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1545">codecov/codecov-action#1545</a></li> <li>build(deps): bump github/codeql-action from 3.26.0 to 3.26.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1551">codecov/codecov-action#1551</a></li> <li>feat: pass tokenless value as branch override by <a href="https://github.com/joseph-sentry"><code>@joseph-sentry</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1511">codecov/codecov-action#1511</a></li> <li>build(deps): bump actions/upload-artifact from 4.3.6 to 4.4.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1563">codecov/codecov-action#1563</a></li> <li>Create makefile.yml by <a href="https://github.com/Hawthorne001"><code>@Hawthorne001</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1555">codecov/codecov-action#1555</a></li> <li>build(deps): bump github/codeql-action from 3.26.2 to 3.26.6 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1562">codecov/codecov-action#1562</a></li> <li>build(deps-dev): bump ts-jest from 29.2.4 to 29.2.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1557">codecov/codecov-action#1557</a></li> <li>Spell <code>evenName</code> in the logs correctly by <a href="https://github.com/webknjaz"><code>@webknjaz</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1560">codecov/codecov-action#1560</a></li> <li>build(deps-dev): bump typescript from 5.5.4 to 5.6.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1566">codecov/codecov-action#1566</a></li> <li>build(deps-dev): bump <code>@types/jest</code> from 29.5.12 to 29.5.13 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1567">codecov/codecov-action#1567</a></li> <li>build(deps): bump github/codeql-action from 3.26.6 to 3.26.7 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1569">codecov/codecov-action#1569</a></li> <li>build(deps-dev): bump eslint from 8.57.0 to 8.57.1 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1571">codecov/codecov-action#1571</a></li> <li>build(deps): bump github/codeql-action from 3.26.7 to 3.26.8 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1575">codecov/codecov-action#1575</a></li> <li>build(deps-dev): bump <code>@vercel/ncc</code> from 0.38.1 to 0.38.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/codecov/codecov-action/pull/1577">codecov/codecov-action#1577</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/codecov/codecov-action/commit/b9fd7d16f6d7d1b5d2bec1a2887e65ceed900238"><code>b9fd7d1</code></a> chore(release):4.6.0 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1587">#1587</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/6f7612c64d7caf2e5f3d18f51fdfc167708e5e4d"><code>6f7612c</code></a> fix: bump eslint parser deps (<a href="https://redirect.github.com/codecov/codecov-action/issues/1586">#1586</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/26c7e28d7e3a90542b75f62e4f1e4191eb53ad20"><code>26c7e28</code></a> build(deps): bump actions/checkout from 4.1.7 to 4.2.0 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1583">#1583</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/6f744f78de377f4f149ffc93565e64c8a670f536"><code>6f744f7</code></a> build(deps): bump github/codeql-action from 3.26.8 to 3.26.9 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1584">#1584</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/543c3d42fc76502218ecdadc04e65dbd2640a67a"><code>543c3d4</code></a> chore: fix typo of OSS (<a href="https://redirect.github.com/codecov/codecov-action/issues/1578">#1578</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/e379426d37e685eaea0ce29fe26dc3579b027c63"><code>e379426</code></a> build(deps-dev): bump <code>@vercel/ncc</code> from 0.38.1 to 0.38.2 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1577">#1577</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/42656e4cb1f70386950b0ec8a4421ee9ba06526e"><code>42656e4</code></a> build(deps): bump github/codeql-action from 3.26.7 to 3.26.8 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1575">#1575</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/2296b6ba9eee85301a5ef2c7c2cdc738faf1f939"><code>2296b6b</code></a> build(deps-dev): bump eslint from 8.57.0 to 8.57.1 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1571">#1571</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/bd77bc323cd6112f528fe493c071212824878695"><code>bd77bc3</code></a> build(deps): bump github/codeql-action from 3.26.6 to 3.26.7 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1569">#1569</a>)</li> <li><a href="https://github.com/codecov/codecov-action/commit/180b964407756d9f1d1629a946b1bda4e5a76d46"><code>180b964</code></a> build(deps-dev): bump <code>@types/jest</code> from 29.5.12 to 29.5.13 (<a href="https://redirect.github.com/codecov/codecov-action/issues/1567">#1567</a>)</li> <li>Additional commits viewable in <a href="https://github.com/codecov/codecov-action/compare/e28ff129e5465c2c0dcc6f003fc735cb6ae0c673...b9fd7d16f6d7d1b5d2bec1a2887e65ceed900238">compare view</a></li> </ul> </details> <br /> [![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=codecov/codecov-action&package-manager=github_actions&previous-version=4.5.0&new-version=4.6.0)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) You can trigger a rebase of this PR by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> > **Note** > Automatic rebases have been disabled on this pull request as it has been open for over 30 days. Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Configuration menu - View commit details
-
Copy full SHA for 362ebe9 - Browse repository at this point
Copy the full SHA 362ebe9View commit details -
[Snippets] Fixed LoopManager::update_loop_ports (#27300)
### Details: - *To remind, `LoopPort` is expression port connected to another expression port which is not in the same Loop. It's like entry (of exit) point of the Loop. It means that some expression port cannot be port of the Loop if all consumers (or sources) are from the same Loop. However, the method `LoopManager::update_loop_ports` sometimes creates these situation. This PR fixes this method. The screenshot below describes this situation: red loop is inner loop and blue loops is outer loop. However, some of output ports of this Loop is inside (green question sign) - invalid situation which is fixed by these changes.* <img width="233" alt="image" src="https://github.com/user-attachments/assets/88bc6faf-edeb-49c0-b262-55922a884725"> - *Added the corresponding checks to validate pass* - *Remove parts in `init_is_incremented` which handle invalid case by `is_incremented=false`.* ### Tickets: - *CVS-156299*
Configuration menu - View commit details
-
Copy full SHA for b6fe65f - Browse repository at this point
Copy the full SHA b6fe65fView commit details -
[GPU] Added convolution_gpu_b_fs_zyx_fsv16_imad shape agnostic kernel (…
…#26404) ### Tickets: - *[148550](https://jira.devtools.intel.com/browse/CVS-148550)*
Configuration menu - View commit details
-
Copy full SHA for d8befa1 - Browse repository at this point
Copy the full SHA d8befa1View commit details -
[PyOV] Migrate benchmark_app from
setup.py
topyproject.toml
(#27305) ### Details: - Added `--no-deps` because `pip wheel .` with `pyproject.toml` would save the `numpy` wheel in cwd - Since requirements are added to the benchmark_app wheel itself, when installing it they'll be pulled from PyPI anyway ### Tickets: - CVS-156008 --------- Signed-off-by: p-wysocki <przemyslaw.wysocki@intel.com> Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 05c365c - Browse repository at this point
Copy the full SHA 05c365cView commit details -
[NPU] Fix compiler clang build (#27405)
### Details: - *Change from define to constexpr and remove unused code* - *Fix clang build* ### Tickets: - *EISW-146067* --------- Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for eabe528 - Browse repository at this point
Copy the full SHA eabe528View commit details -
[PyOV] Use
python -m build
only for oldpip
versions (#27429)### Details: - An alternative to #27426 - The functionality branching based on pip version has recently been removed in #27190 - This fix has originated from discussion at https://github.com/openvinotoolkit/openvino/pull/27190/files#r1830707810 - Fix for issues with NPU building on Windows machines - A disadvantage is that we need to have `build` as a dependency no matter what, there's no environment marker for `pip` version which would allow us to install it conditionally ### Tickets: - EISW-146038 Signed-off-by: p-wysocki <przemyslaw.wysocki@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6c71599 - Browse repository at this point
Copy the full SHA 6c71599View commit details -
[GHA] WA parallel make issue (#27422)
### Details: - To address the issue mentioned [here](https://unix.stackexchange.com/questions/316644/is-make-j-with-no-argument-dangerous), we need to set the number of parallel jobs explicitly ### Tickets: - *156361*
Configuration menu - View commit details
-
Copy full SHA for 95d6be2 - Browse repository at this point
Copy the full SHA 95d6be2View commit details -
[GPU] Fix accuracy issue in PagedAttention kernel for large prompts (#…
…27433) ### Details: - Fix accuracy issue in PagedAttention kernel for large prompts (4K/8K tokens) by correcting index calculation in sub_group_broadcast function to ensure accurate data broadcasting within the subgroup ### Tickets: - [CVS-154881](https://jira.devtools.intel.com/browse/CVS-154881)
Configuration menu - View commit details
-
Copy full SHA for 42d4377 - Browse repository at this point
Copy the full SHA 42d4377View commit details -
Configuration menu - View commit details
-
Copy full SHA for 33cba00 - Browse repository at this point
Copy the full SHA 33cba00View commit details
Commits on Nov 7, 2024
-
[GHA] Coverity build regression fix (#27445)
### Details: - Fixed regression introduced by #27422 ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 9226bbe - Browse repository at this point
Copy the full SHA 9226bbeView commit details -
[GPU] Enable KV-cache compression by default for non-systolic platfor…
…ms (#27410) ### Details: - Enable KV-cache compression by default for non-systolic platforms
Configuration menu - View commit details
-
Copy full SHA for 5fad805 - Browse repository at this point
Copy the full SHA 5fad805View commit details -
[Snippets] Added dynamic memory sharing support (#27175)
### Details: - *Added memory inplace support for Buffer with different precision (it's supported only when output Buffer has data size not more than input Buffer) - it's needed for BF16 and INT8 MHA* - *Added memory inplace support for dynamic Buffers with the marking pass "MarkInvariantShapePath"* ### Tickets: - *154732, 150148* ### Prerequisites: - [x] #27169 - [x] #27300
Configuration menu - View commit details
-
Copy full SHA for ab71e5b - Browse repository at this point
Copy the full SHA ab71e5bView commit details -
[CPU] Roll back deconv 3rd rank layout order for non AMX (#27446)
### Details: - *temporal WA limiting Deconv acb Layout to avx512_core_amx_fp16 platform before oneDNN fix the performance regression issue of related primitive creation* ### Tickets: - *CVS-156640*
Configuration menu - View commit details
-
Copy full SHA for 696bdde - Browse repository at this point
Copy the full SHA 696bddeView commit details -
[GHA] Increase timeout for PyTorch Models tests in precommit (#27449)
### Tickets: - 155619
Configuration menu - View commit details
-
Copy full SHA for a9ddd47 - Browse repository at this point
Copy the full SHA a9ddd47View commit details -
[GHA][Coverity] Disable sccache (#27450)
### Details: - sccache doesn't properly work with Coverity ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 98f6ea5 - Browse repository at this point
Copy the full SHA 98f6ea5View commit details -
[PT FE] Inherit signature from forward while patching (#27413)
### Details: - *Inherit signature from forward while patching* ### Tickets: - *ticket-id* --------- Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 5c83460 - Browse repository at this point
Copy the full SHA 5c83460View commit details -
Sns enable lp kn blocking (#26957)
### Details: - *Perform weights repacking outside of the blocking cycles* - *Functionally enable blocking for I8,U8 and BF16* - *The blocking will be temporary disabled until blocking heuristic is updated in 156014* ### Tickets: - *154729*
Configuration menu - View commit details
-
Copy full SHA for 8edb150 - Browse repository at this point
Copy the full SHA 8edb150View commit details -
Improve SIT to compose a batch tensor as a model input make up from a…
… packet of different images (#27341) ### Details: - A new parameter `override_model_batch_size` was added several PRs ago. The purpose of this parameter was is to take a picture/binary and "stretch" it to fit a batched tensor as an input of a batched model providing that we could run and validate batched models - The current PR enhance this idea and allows us to set distinguished images/binaries in a batched tensor input so that we could validate correctness of processing of different lines of batch during our inference invocations. SIT now uses "|" separator to discern different images inside input images array as an command line argument. The batched images filing algorithm is the following: 1) If passed images amount is not enough to fill up an entire batch, a last image will be propagated and copied to remnant lines of N-batch. 2) If passed images array is larger than an batched tensor, then only N images will be used up and the rest of images will be thrown away Example: ``` single-image-test --device CPU --network resnet50.xml --mode classification --top_k 5 --il NCHW --ol NC --iml NCHW --oml NC --ip FP16 --op FP16 --override_model_batch_size 3 --input "dog.bmp|00000001.JPEG|00000002.JPEG" ``` gives us ``` ... Load input #0 from [dog.bmp,00000001.JPEG,00000002.JPEG] as f16 [N,C,H,W] [3,3,224,224] Fill up all input batch slices planes up to 3 with image data from the array: [0/3] Fill input batch slices planes starting from index 1 up to 3 with image data from the array: [1/3] Fill input batch slices planes starting from index 2 up to 3 with image data from the array: [2/3] ``` ### Tickets: - E####145303 --------- Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f33a637 - Browse repository at this point
Copy the full SHA f33a637View commit details -
[GHA] Enable Fedora trigger in post-commit (#27463)
We need that to have build artifacts stored from pushes Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b416fb0 - Browse repository at this point
Copy the full SHA b416fb0View commit details
Commits on Nov 8, 2024
-
[GPU] Add check to fallback to permute_ref if different format for on…
…eDNN (#27402) ### Details: If the input and output format are not the same in permute before oneDNN convolution, permute_kernel_f_y_axes doesn't support it. Need to fallback to permute_ref ### Tickets: - *CVS-155933*
Configuration menu - View commit details
-
Copy full SHA for fb5b5ed - Browse repository at this point
Copy the full SHA fb5b5edView commit details -
[GPU] Fix one hot seg fault when the second input node is not a Const…
…ant node (#27442) ### Details: - *Get the 'depth' value from 'Select' node instead of a Constant node* This happens when the second input of **OneHot** node is not a **Constant** node (**Select** node in this PR). ![image](https://github.com/user-attachments/assets/1bef5fdd-ae42-4916-9ba1-46b8d397e34b) ### Tickets: - *[CVS-155564](https://jira.devtools.intel.com/browse/CVS-155564)* --------- Signed-off-by: yuan.xiong <yuan.xiong@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 5e6fb3c - Browse repository at this point
Copy the full SHA 5e6fb3cView commit details -
[Benchmark App] Reject -nireq > -niter when using sync API (#27460)
### Details: While investigating the problem raised by the E-117106 ticket, turned out that, in fact, a problem lies within the Benchmark App. When choosing the sync API, it is not possible to run more inference requests than specified iterations. Later on, if `-pc` flag was given, the app still tries to display the profiling data for the never launched inferences. This PR detects this situation and rejects the application execution after writing an explanatory message to the console output. Changes are applied for both C++ and Python versions of the benchmark app. ### Tickets: - CVS-156823 Co-authored-by: Vladimir Zlobin <vladimir.zlobin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 9ff42cd - Browse repository at this point
Copy the full SHA 9ff42cdView commit details -
[GPU] Don't select add_fusing_type::sum when dependency is input_layo…
…ut in loop body network (#27443) ### Details: - Don't select add_fusing_type::sum when dependency is input_layout in loop body network. sum op could contaminate memory buffer. ### Tickets: - 154020
Configuration menu - View commit details
-
Copy full SHA for bb99d67 - Browse repository at this point
Copy the full SHA bb99d67View commit details -
[DOCS] benchmark data tweaks (#27424)
Co-authored-by: Andrzej Kopytko <andrzejx.kopytko@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 406034d - Browse repository at this point
Copy the full SHA 406034dView commit details -
[Opset] Opset16 initialization (#27458)
### Details: - Initialization of OV Opset16 ### Tickets: - 156876, Finalization 156877
Configuration menu - View commit details
-
Copy full SHA for 704de6e - Browse repository at this point
Copy the full SHA 704de6eView commit details -
Docs new benchmark grapf with two y axis (#27480)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 3826706 - Browse repository at this point
Copy the full SHA 3826706View commit details -
[NPU] Use level zero init structure/ Follow same code design (#27453)
### Details: - *Use init structure instead of raw pointers to make sure the methods are still available* - *Use the same design in case of shared_ptr* ### Tickets: - *EISW-94929* --------- Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 51062ea - Browse repository at this point
Copy the full SHA 51062eaView commit details -
[GHA] Exclude AND conditions in the allowed licenses list (#27478)
### Details: - Addressed actions/dependency-review-action#842 ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 8bfd994 - Browse repository at this point
Copy the full SHA 8bfd994View commit details -
[GHA] Enable Ubuntu 20 arm in postcommits (#27485)
Needed to have post-commit artifacts for packaging Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6ae3f9f - Browse repository at this point
Copy the full SHA 6ae3f9fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 6aaddd5 - Browse repository at this point
Copy the full SHA 6aaddd5View commit details -
[PyAPI] Add Identity-16 Operation (#26717)
### Details: - Extends Python API with Identity operation - Identity op Core/Ref files should disappear after merging: #26716 ### Tickets: - 152728 --------- Co-authored-by: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3c5744e - Browse repository at this point
Copy the full SHA 3c5744eView commit details
Commits on Nov 11, 2024
-
Updated NNCF Weight Compression README (#27448)
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 22f3fef - Browse repository at this point
Copy the full SHA 22f3fefView commit details -
[DOCS] Use
gpg
instead ofapt-key add
to add the GPG key to APT k……eyrings directory (#26922) ### Details: Since `apt-key add` is deprecated, I tried by myself to instead use the `gpg` command to add the GPG key to APT keyrings directory. This is what I tried on my own: <https://gist.github.com/ytxmobile98/b198a8ef4d2affd713780b16159a6618#file-install-md> ### Tickets: - *ticket-id* Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b8743fc - Browse repository at this point
Copy the full SHA b8743fcView commit details -
[PT FE] Optimize memory usage of patch_model (#27428)
### Details: - *`no_jit_trace` was using extra memory to get and store trace state, which contained all graph that was produced before, that increase memory consumption of tracing. For example for FLUX model it used about 20Gb of extra memory* - *Saving `args` on meta device didn't work without `no_jit_trace`. To workaround this issue we now pass args directly to forward without saving them in `Trampoline`. This allows better flow for arguments and reduce memory used to save those args. However this changes the behavior of `evaluate` of `ModuleExtension`, because now it uses the args that were passed to `convert` and not the original args.* optimum-cli for FLUX with `torch_dtype=torch.bfloat16` before change: ![image](https://github.com/user-attachments/assets/f070068a-e52e-4558-956e-95afa64d1dbc) optimum-cli for FLUX with `torch_dtype=torch.bfloat16` after change: ![image](https://github.com/user-attachments/assets/a76fe1df-2410-4b92-9b01-38ef40133b2b) Note: optimum doesn't yet support `torch_dtype=torch.bfloat16` for FLUX. ### Tickets: - *CVS-151254* --------- Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
Configuration menu - View commit details
-
Copy full SHA for f9118af - Browse repository at this point
Copy the full SHA f9118afView commit details -
[EISW-136980][NPU] Remove use_elf_compiler_backend option (#26518)
### Details: - After GF schema removal https://jira.devtools.intel.com/browse/EISW-129562 there is no need to have use_elf_compiler_backend option as ELF backend set by default. ### Tickets: - https://jira.devtools.intel.com/browse/EISW-136980
Configuration menu - View commit details
-
Copy full SHA for 999d678 - Browse repository at this point
Copy the full SHA 999d678View commit details -
[opset1::Reshape] Deduce symbol relation based on op spec (#27399)
### Details: - *Number of elements in the tensor doesn't change after Reshape operation, so we can deduce symbol equality rules* ``` [A, B, 768] Reshape [A, C, 12, 64] ``` From this Reshape operation we can deduce that `B == C`. ![image](https://github.com/user-attachments/assets/f59dca8f-9d4d-4bc7-ade1-9ea47b78e06a) --------- Signed-off-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 539a2ac - Browse repository at this point
Copy the full SHA 539a2acView commit details -
[GPU] Fix SDPA shape inference issue (#27471)
### Details: Fix SDPA shape inference issue ### Tickets: - *CVS-151301*
Configuration menu - View commit details
-
Copy full SHA for 0a53629 - Browse repository at this point
Copy the full SHA 0a53629View commit details -
[NPUW] Fix bank weak_ptr (#27488)
After CompiledModel object is deleted, shared_ptr<Bank> is reset - thus expiring weak_ptr in bank manager class. If we try to create a CompiledModel object again with the same bank name - it was trying to utilize already empty bank ptr. This PR fixes such case Release branch PR #27486
Configuration menu - View commit details
-
Copy full SHA for d9109f6 - Browse repository at this point
Copy the full SHA d9109f6View commit details -
[TF FE] Support Expm1 operation (#27491)
**Details:** Support Expm1 operation **Ticket:** TBD --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 4dc005e - Browse repository at this point
Copy the full SHA 4dc005eView commit details -
[CPU][ARM] Fix performance issues in deconvolution layer (#27466)
### Details: - Perf degradation - Noise Suppression Poconet-Like FP16 ### Tickets: - CVS-156953
Configuration menu - View commit details
-
Copy full SHA for e1fdf7b - Browse repository at this point
Copy the full SHA e1fdf7bView commit details -
[NPU] Adjust wording to avoid confusion when running benchmarks (#27455)
### Details: While investigating the problem raised by the EISW-117106 ticket, turned out that, in fact, a problem lies within the Benchmark App. For that problem, we've filed a separate ticket CVS-156823 and here we adjust the wording, aiming to reduce end-user confusion. ### Tickets: - E-117106
Configuration menu - View commit details
-
Copy full SHA for c5d9001 - Browse repository at this point
Copy the full SHA c5d9001View commit details -
[CI] [GHA] Set pip cache directory correctly on Windows (#27456)
### Tickets: - *155314*
Configuration menu - View commit details
-
Copy full SHA for 05e12d0 - Browse repository at this point
Copy the full SHA 05e12d0View commit details -
Implement runtime scatter update skippable (#27439)
### Details: - *Fix the memory corruption error found runtime skipped nodes for scatter element update* - *Implement do_runtime_scatter_update_skippable* - *Add scatter_update to mark_runtime_skippable_nodes* - *Update memory clearing codes to support the following cases:* - ***Issued case1*** - *iter0: node1(executed) -> node2(skipped) -> node3(skipped)* - *iter1: node1(skipped) -> node2(skipped) -> node3(executed)* - ***Issued case2*** - *iter0: node1(skipped) -> node2(skipped) -> node3(skipped)* - *iter1: node1(executed) -> node2(skipped) -> node3(executed)* ### Tickets: - *154591*
Configuration menu - View commit details
-
Copy full SHA for 602f701 - Browse repository at this point
Copy the full SHA 602f701View commit details
Commits on Nov 12, 2024
-
[Spec] Identity operation (#26718)
### Details: - Adds opset15 spec - Adds Identity specification - To be merged after #26717 Question for review - is "activation" the correct folder to place this op into, or would "internal" be better? ### Tickets: - 152730 --------- Signed-off-by: PiotrKrzem <piotr.krzeminski@intel.com> Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 339a091 - Browse repository at this point
Copy the full SHA 339a091View commit details -
[Range] Symbol propagation for range from 0 to A (#27505)
### Details: - *Symbol propagation for Range [0:A:1]* --------- Signed-off-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com>
Configuration menu - View commit details
-
Copy full SHA for b5a4ad1 - Browse repository at this point
Copy the full SHA b5a4ad1View commit details -
[TF Quant Models] Prepares GroupConvolution weights (#25641)
### Details: - *using register_new_node in the matches to allow for seamless matcher application for the FQ node* - *added optional Convert node, so that pattern would work on different quantized weights forms* ![image](https://github.com/user-attachments/assets/2d485f5b-7609-40ac-b798-16124a9a290a) ### Tickets: - *CVS-39818*
Configuration menu - View commit details
-
Copy full SHA for ff4d1e5 - Browse repository at this point
Copy the full SHA ff4d1e5View commit details -
update notebooks list in README (#27496)
### Tickets: - *CVS-156989* --------- Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 0206cd1 - Browse repository at this point
Copy the full SHA 0206cd1View commit details -
update latency configuration for multi numa nodes on one socket (#26798)
### Details: - *For multi numa nodes per socket platform, default latency behavior is running inference on one numa node which application is running* - *Update this logic to both Linux and Windows* - *PR #26944 is document change* ### Tickets: - *CVS-140601*
Configuration menu - View commit details
-
Copy full SHA for 72bf426 - Browse repository at this point
Copy the full SHA 72bf426View commit details -
[TF FE] Remove unused vars for DepthwiseConv2d operation (#27519)
**Details:** Remove unused vars for DepthwiseConv2d operation **Ticket:** TBD Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 6aca1f6 - Browse repository at this point
Copy the full SHA 6aca1f6View commit details -
update document for latency configuration for multi numa nodes on one…
… socket (#26944) ### Details: - *update document for latency configuration for multi numa nodes on one socket* - *PR #26798 is code change* ### Tickets: - *CVS-140601*
Configuration menu - View commit details
-
Copy full SHA for dbc14b2 - Browse repository at this point
Copy the full SHA dbc14b2View commit details -
[OV JS] Make download binaries script universal (#27465)
### Details: - Implement **BinaryManager** class that configurable and universal - Extract helpers logic into utils - Make `download-binaries` script short and readable ### Tickets: - 156951 --------- Co-authored-by: Alicja Miloszewska <alicja.miloszewska@intel.com>
Configuration menu - View commit details
-
Copy full SHA for c6cc97c - Browse repository at this point
Copy the full SHA c6cc97cView commit details -
[PyOV] Improve import_model memory consumption (#27451)
### Details: - Writing to stringstream caused additional copy - Usage of fstream also caused extra memory usage. Also we needed to proper handle saving/removal of the tmp_file. - So I've squeezed two `import_model` methods to one and I've implemented/reused custom buffer that wraps interactions with python memory without extra copies ### Tickets: - EISW-137436
Configuration menu - View commit details
-
Copy full SHA for 7880504 - Browse repository at this point
Copy the full SHA 7880504View commit details -
[DOCS] Refactor two y-axis graph scripts (#27524)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 629fb81 - Browse repository at this point
Copy the full SHA 629fb81View commit details -
[GPU] fix bad_fuction call issue (#27517)
### Details: - *Fix bad_function call issue which is caused by creating empty kernel_data* - Reverting some change applied at #27439 - To be investigated and fixed in the next PR ### Tickets: - *154591*
Configuration menu - View commit details
-
Copy full SHA for 0080d90 - Browse repository at this point
Copy the full SHA 0080d90View commit details
Commits on Nov 13, 2024
-
[CPU] Enable u8 kv cache by default (#27454)
### Details: - *Enable u8 kv cache by default* - *...* ### Tickets: - *[152621](https://jira.devtools.intel.com/browse/CVS-152621)*
Configuration menu - View commit details
-
Copy full SHA for 2d148ec - Browse repository at this point
Copy the full SHA 2d148ecView commit details -
fix assertion failed on lockable_mem when using devicemem (#27297)
### Details: - *The issue caused by the memory select of the input. In the changed behavior called locked memory will put the input into host memory if any the implementation of its users is CPU.* - *when the input is set to "use_device_mem" by benchmark_app, the locked memory will ignore the memory, which will trigger the assertion failure.* - *fixed just ignore "need_lockable_mem" option in case of remote tensors, because the data could be cloned implicitly at attempt to access device buffer from the host side to have this copy* ### Tickets: - *CSV-152365*
Configuration menu - View commit details
-
Copy full SHA for 41c1400 - Browse repository at this point
Copy the full SHA 41c1400View commit details -
Add parameter to execute inference requests at a fixed frequency (#26820
Configuration menu - View commit details
-
Copy full SHA for 79dd358 - Browse repository at this point
Copy the full SHA 79dd358View commit details -
Enable weightless caching with compile_model() API without providing …
Configuration menu - View commit details
-
Copy full SHA for a58202f - Browse repository at this point
Copy the full SHA a58202fView commit details -
[Templ test] GroupConvolutionBackpropData: Enable whole Tensor compar…
…ison (#27379) ### Details: - Enabled whole tensor comparison. ### Tickets: - CVS-137167 Signed-off-by: Tomasz Jankowski <tomasz1.jankowski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 291d3e1 - Browse repository at this point
Copy the full SHA 291d3e1View commit details -
[GPU] Minor state fixes (#27508)
### Tickets: - *[152882](https://jira.devtools.intel.com/browse/CVS-152882)*
Configuration menu - View commit details
-
Copy full SHA for 431202e - Browse repository at this point
Copy the full SHA 431202eView commit details -
[TRANSFORMATIONS | GPU] Add a Validate pass after MoveEltwiseUpThroug…
…hDataMovScalar for element type resolution (#27464) [TRANSFORMATIONS | GPU] Add a Validate pass after MoveEltwiseUpThroughDataMovScalar After executing the MoveEltwiseUpThroughDataMovScalar transforamtion some node's element types may appear to be in inconsistent/corrupted state. Fix it by inserting a Validate pass after the transformation for resolving the node's element types. This commit is a workaround until the 141764 is fixed which resolves the issue of Validate passes. Ticket: * CVS-151111 Signed-off-by: Andrii Staikov <andrii.staikov@intel.com> Signed-off-by: Andrii Staikov <andrii.staikov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for acccb22 - Browse repository at this point
Copy the full SHA acccb22View commit details -
[DOCS] Fixing reference in documentation (#27531)
Fixing broken links in documentation. Signed-off-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Configuration menu - View commit details
-
Copy full SHA for d5dcb04 - Browse repository at this point
Copy the full SHA d5dcb04View commit details -
[CI][GHA] Manylinux x86 build (#27430)
### Details: - Enabled manilinux x86 build based on manylinux 2014 image - OpenVINO tarball package - Wheels for 3.9-3.13 Pythons ### Tickets: - *148719* --------- Co-authored-by: Alina Kladieva <alina.kladieva@intel.com> Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
Configuration menu - View commit details
-
Copy full SHA for a97ff61 - Browse repository at this point
Copy the full SHA a97ff61View commit details -
[PyOV] Restrict changing data in const (#27431)
### Details: - Const op meant to be non-changeable ### Tickets: - CVS-124319
Configuration menu - View commit details
-
Copy full SHA for a0940bb - Browse repository at this point
Copy the full SHA a0940bbView commit details -
[DOCS] Preselection and sorting (#27538)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for eb38e67 - Browse repository at this point
Copy the full SHA eb38e67View commit details -
[DOCS] fixed get_cmake_path import instructions (#27542)
### Details: - Fixed import example ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 4847f49 - Browse repository at this point
Copy the full SHA 4847f49View commit details -
[core] On Linux try return not used memory to system on compile model…
… destructor (#27534) ### Details: - Optimize Linux process using OV memory consumption by returning not used memory to the system when compiled model is destroyed. - It should optimize memory usage by C++ and Python applications, as Linux avoid reclaim memory until process end especially for small chunks of allocations. ### Tickets: - CVS-149497
Configuration menu - View commit details
-
Copy full SHA for f417097 - Browse repository at this point
Copy the full SHA f417097View commit details -
Configuration menu - View commit details
-
Copy full SHA for 51906cf - Browse repository at this point
Copy the full SHA 51906cfView commit details -
Configuration menu - View commit details
-
Copy full SHA for 3d4f942 - Browse repository at this point
Copy the full SHA 3d4f942View commit details -
[DOCS] Security best practices for GitHub Actions workflows developme…
…nt (#27394) ### Details: Security guidelines for GitHub Actions workflows developers
Configuration menu - View commit details
-
Copy full SHA for d70603e - Browse repository at this point
Copy the full SHA d70603eView commit details
Commits on Nov 14, 2024
-
[GPU] Fix unexpectedly turned off Small N case optimization (#27493)
### Details: - In https://github.com/openvinotoolkit/openvino/pull/26733/files, small N case optimization with tile_ofm == 1 was unexpectedly turned off ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 2b25007 - Browse repository at this point
Copy the full SHA 2b25007View commit details -
[GPU] Fix memory leak (#27536)
### Details: - Fix memory leak and improve memory usage with continuous inference ### Tickets: - 148552
Configuration menu - View commit details
-
Copy full SHA for b1ff99c - Browse repository at this point
Copy the full SHA b1ff99cView commit details -
[TF FE] Stabilize layer tests for Keras GRU layer on all platforms (#…
…27543) **Details:** Stabilize layer tests for Keras GRU layer on all platforms **Ticket:** 156967 --------- Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 453ee57 - Browse repository at this point
Copy the full SHA 453ee57View commit details -
[CPU]fix rope mark up to skip shapeof (#27462)
### Details: - *Stop markup at ShapeOf* - *The ShapeOf in the subgraph of Rope's 2nd/3rd input should not be marked* - *The parent of ShapeOf may change when IR changes so skip it to avoid unknown precision problem* ### Tickets: - *CVS-155898*
Configuration menu - View commit details
-
Copy full SHA for a661f0d - Browse repository at this point
Copy the full SHA a661f0dView commit details -
Fixed OVC app name in telemetry. (#27544)
### Details: - Fixed the issue, that '`Model Conversion API`' telemetry category includes `OVC` and all other tools, now `OVC` has a separate category "`OVC`". - Refactored `send_params_info()` method and fixed naming of telemetry init method. --------- Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com>
Configuration menu - View commit details
-
Copy full SHA for fefe0c3 - Browse repository at this point
Copy the full SHA fefe0c3View commit details -
[GHA] Manylinux added CI tags and manifest (#27540)
### Details: - added actions to save artifacts for Jenkins - create_manifest and store_artifacts - Added overall status workflow ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 19ae2a9 - Browse repository at this point
Copy the full SHA 19ae2a9View commit details
Commits on Nov 15, 2024
-
[GPU] Change weights_path mutabilibity to RW (#27553)
### Details: It needs to be readable (e.g. to be queried by hello_query_device sample) and writable for plugin to set the default value. ### Tickets: https://jira.devtools.intel.com/browse/CVS-157364
Configuration menu - View commit details
-
Copy full SHA for 651a51c - Browse repository at this point
Copy the full SHA 651a51cView commit details -
[DOCS] Updating NPU GenAI docs (#27489)
Updating the `Run LLMs with OpenVINO GenAI Flavor on NPU` article - adding info about new config options. This PR addresses JIRA ticket: 156503. --------- Signed-off-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Configuration menu - View commit details
-
Copy full SHA for c338559 - Browse repository at this point
Copy the full SHA c338559View commit details -
[DOCS Added new hierarchical field for Coveo (#27569)
### Details: - *item1* - *...* ### Tickets: - *ticket-id*
Configuration menu - View commit details
-
Copy full SHA for 250f001 - Browse repository at this point
Copy the full SHA 250f001View commit details -
fix TSUnsqueezeBackward Reshape does nothing (#27467)
### Details: - fix TSUnsqueezeBackward ### Tickets: - CVS-111560
Configuration menu - View commit details
-
Copy full SHA for 6489755 - Browse repository at this point
Copy the full SHA 6489755View commit details -
[NPU] Remove template in ext wrapper and fuse functions (#27511)
### Details: - *Remove template in zero_ext_graph_wrappers* - *Remove zero_ext_graph_wrappers_interface.hpp* - *Add more low level debug log* - *Update level-zero-ext repo commit to use 1.9 version* ### Tickets: - *156387* --------- Signed-off-by: Xin Wang <xin1.wang@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 3e63de0 - Browse repository at this point
Copy the full SHA 3e63de0View commit details -
[DOCS] Updating Weight Compression Article (#27432)
Rearranging information in the `LLM Weight Compression` article. --------- Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
Configuration menu - View commit details
-
Copy full SHA for 0376890 - Browse repository at this point
Copy the full SHA 0376890View commit details