Changes from upstream/master #2
Open
+653,699
−566,407
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
category: build
category: C API
category: CI
github_actions
category: Core
category: CPP API
category: CPU
category: dependency_changes
category: docs
category: GPU
category: NPU
category: IE Tests
category: inference
category: packaging
category: Python API
category: JS API
category: TEMPLATE
category: TF FE
category: TFL FE
category: PyTorch FE
no-match-files
labels
Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
Required for internal tests using requirement files packed here Signed-off-by: Alina Kladieva <alina.kladieva@intel.com>
+ Add reorder to change input format from blocked to plain for dGPU to select onednn kernel for gemm. ### Tickets: - *162459*
Implicit casting error when different input and output data type. Use in_type instead of out_type during FUSED_OPS_VEC. ### Tickets: - *160534* --------- Signed-off-by: hyunback <hyunback.kim@intel.com>
### Details: - *Use the new ZE_MUTABLE_COMMAND_EXP_FLAG_GRAPH_ARGUMENTS flag -> if the flag is still not supported by the driver, fallback to the deprecated one* - *Create fences or events only if they are used* - *Check Major version correctly* - *Make sure the Command queue is kept alive until the Fence is destroyed* - *Removing unused parameters from compiler adapter* --------- Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
By utilizing the fact, that the base edge is always the first edge in the cluster. This helps to avoid unnecessary looping when updating the referencing edges. Also allocated dynamic output edges before the regions are created, so there is no need to create those regions and then removed them anyway.
Reverts #29031 because it introduced sporadic failures (e.g.: https://github.com/openvinotoolkit/openvino/actions/runs/13432909164/job/37528579365?pr=29086) The licenses whitelist should not contain AND expressions (see actions/dependency-review-action#842)
### Details:
After switching from ModelOptimizer to OVC, the order of
applying PrePostProcessing and MOCTransformations has changed:
MO path : [fw model conversion -> PrePostProcessing -> MOC] -> nncf
OVC path: [fw model conversion -> MOC] -> PrePostProcessing -> nncf
Since nncf is applied with a not fully optimized model, extra FQ ops
might appear,
which can affect both accuracy and performance.
e.g. Mul -> Conv fusion is not applied due to extra FQ
<img width="165" alt="{C6E93F2C-2CE3-4596-8D7F-ED7BD8013603}"
src="https://github.com/user-attachments/assets/3cbe6e07-9c07-4002-8b4c-9fb5bc662421"
/>
PrePostProcessing is not part of OVC, so we have to insert additional
Transformation calls inside PrePostProcessing.
### Tickets:
- *CVS-160786*
- CVS-161724
---------
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Andrii Staikov <andrii.staikov@intel.com>
### Details: - Mark `ov::element::undefined` as deprecated - Use dynamic type instead of undefined ### Related PRs: - openvinotoolkit/openvino_contrib#945 - #28524 ### Tickets: - CVS-161637 --------- Signed-off-by: Pawel Raasz <pawel.raasz@intel.com> Signed-off-by: Raasz, Pawel <pawel.raasz@intel.com>
) ### Details: - Add utils to core to set names on model input/output tensors - Define default tensor names and port separator - Use auto naming in model created by python API. Model outputs will have got names also. - The auto naming can be part of Model API but requires to add validation tools to find and resolve names collision - Auto naming cannot be added to Model creation in C++ as it can have impact on (de)serialization, requires more investigation ### Tickets: - CVS-159997 --------- Signed-off-by: Raasz, Pawel <pawel.raasz@intel.com>
### Details: - *item1* - *...* ### Tickets: - *ticket-id* Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
### Details: - *Reverted `reset_state()` change (no changes regarding `reset_state()` is presented here regardless of branch name)* - *Added initialization of tensors in LLMInferRequest* - *Fixed copy of attention_mask* ### Tickets: - *ticket-id*
### Details: - *Return default NonZero type where possible. This allows to merge two NonZero nodes.* ### Tickets: - *CVS-160578* Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
### Details: - *Extend mean_iou metric in single-image-test for semantic segmentation networks that have ArgMax at the end.* ### Tickets: - *EISW-158075*
### Details: - *Fix turbo mode* ### Tickets: - *E#156694* Signed-off-by: Bogdan Pereanu <bogdan.pereanu@intel.com>
### Details: - *Allows symbolic matching, see details in a presentation in a ticket* ### Tickets: - *CVS-162241* --------- Signed-off-by: Evgeniia Nugmanova <evgeniia.nugmanova@intel.com> Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
### Details: - Tensor creation from Pillow Image ### Tickets: - CVS-156053
### Details: - Fix "bugprone-fold-init-type" remarks reported by clang-tidy - Enable "bugprone-fold-init-type" clang-tidy checks on CI by default ### Tickets: - N/A
### Details: - added input idx calculation because output idx was different due to output padding - part of accuracy fix of model FasterRCNN_ResNet50_FPN_V2.onnx ### Tickets: - small part of 101294
### Details: - *Currently, `MatMulTransformation` has unnecessary limitation on zero point values. This PR removes the useless check.* - *Correctness of the changes confirmed by new test cases in CPU/GPU plugin tests.*
… in sdpa_opt_finalization_stage (#29083) ### Details: - To replaced local_memory with shared_local_memory to prevent index conflicts and save local memory by updating the definition of max_logits_u_exp_sum. - To remove redundant code to improve maintainability. ### Tickets: - CVS-162803 Co-authored-by: Chen Peter <peter.chen@intel.com>
### Details: - In current approach for lazy import, we use `importlib.util.LazyLoader`. This approach first creates a module, adds it to python `sys.module`s, and then LazyLoader executes the module when sb tries to access e.g. `openvino.runtime` attribute. - The issue is that in this approach `openvino.runtime` might be initialized too early, e.g. by [`inspect` module](https://github.com/python/cpython/blob/140e69c4a878d7a0a26d4406bdad55e56ddae0b7/Lib/inspect.py#L915) which iterates over modules present in `sys.modules`, e.g.:  Proposal: - Change the lazy loading approach. Import `openvino.runtime` and add it to `sys.modules` only when an attribute is accessed. Possible thanks to overloading `__getattr__` and `__dir__` methods.  ### Tickets: - *ticket-id* --------- Signed-off-by: Alicja Miloszewska <alicja.miloszewska@intel.com>
### Details: - *item1* - *...* ### Tickets: - *ticket-id* --------- Co-authored-by: Anastasiya Pronina <anastasiya.pronina@intel.com>
…n layers (#28868) ### Details: - Fixed lower/upper bounds for inserted FakeQuantize between layers ### Tickets: - 157882
…e constant (#29065) ### Details: - *Optimize `normalize_axis` for case when axis is already positive constant* ### Tickets: - *CVS-161495* --------- Signed-off-by: Maxim Vafin <maxim.vafin@intel.com>
### Details: - the consumer count should be 1, as the pass is rotating the nodes, otherwise the shapes of related nodes will be messed up ### Tickets: - CVS-162530 --------- Signed-off-by: fishbell <bell.song@intel.com> Co-authored-by: Chen Peter <peter.chen@intel.com>
…rc/bindings/python (#29082) Updates the requirements on [h5py](https://github.com/h5py/h5py) to permit the latest version. <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/h5py/h5py/commit/c96b93d9ca3a92741c0b2476554f9026cdd47e00"><code>c96b93d</code></a> Merge pull request <a href="https://redirect.github.com/h5py/h5py/issues/2559">#2559</a> from h5py/changelog-3.13</li> <li><a href="https://github.com/h5py/h5py/commit/04daabc6529d84eb223ade750728d9a70659f12e"><code>04daabc</code></a> Add docstring for SpaceId.select_shape_same</li> <li><a href="https://github.com/h5py/h5py/commit/0588148c1f33721b5a52f01cc8725c72d7283d0b"><code>0588148</code></a> Full import path to low-level method</li> <li><a href="https://github.com/h5py/h5py/commit/584b591d3868e9764a85677662b3f57ca1a1163d"><code>584b591</code></a> Add release notes for 3.13</li> <li><a href="https://github.com/h5py/h5py/commit/a04f03cdc4f1df54034d8a39d89e6d541c2fd13a"><code>a04f03c</code></a> Version number -> 3.13</li> <li><a href="https://github.com/h5py/h5py/commit/f416f89857be681a82a8d23fb320f70c65d61876"><code>f416f89</code></a> Merge pull request <a href="https://redirect.github.com/h5py/h5py/issues/2517">#2517</a> from takluyver/in-memory</li> <li><a href="https://github.com/h5py/h5py/commit/7bc2c191a8c802798c86bc3c2c0e60a2228884d3"><code>7bc2c19</code></a> Use a different make_fapl() parameter to test File.in_memory()</li> <li><a href="https://github.com/h5py/h5py/commit/3a7bd67e1d11fa04d6193b606b711498523b5f6f"><code>3a7bd67</code></a> Add news entry for File.in_memory()</li> <li><a href="https://github.com/h5py/h5py/commit/261f6099f10bd0deb6f641d4d86c8769706a3223"><code>261f609</code></a> Fix passing make_fcpl() keyword arguments from File.in_memory()</li> <li><a href="https://github.com/h5py/h5py/commit/c8a141ba9c94631939b4d12634fff99c87ed5b5f"><code>c8a141b</code></a> Fix default block size in docs</li> <li>Additional commits viewable in <a href="https://github.com/h5py/h5py/compare/3.1.0...3.13.0">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>
### Details: - In the current `fc_bf_tiled_forced_tile_b` kernel, when `TILE_OFM=1`, `acc_tmp` becomes a one-dimensional array rather than two-dimensional array that process vector type, so issue may occur in the process of obtaining `acc` from `acc_tmp` and initializing `acc_tmp` - Fix this issued case for `fc_bf_tilied_forced_tile_b` kernel ### Tickets: - 162831
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.