Implemented Tensor.setShape in Node.js API #29842
Open
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
) ### Details: Should fix the `semgrep` check like https://github.com/openvinotoolkit/openvino/actions/runs/13967955280/job/39102642828 ### Tickets: - *164607*
…tage (openvinotoolkit#29672) ### Details: - *To reduce overheads in runtime, we moved repacking of second constant input of `Brgemm` from inference stage to model compilation stage.* - *Introduced helper `utils::get_planar_layout`* ### Tickets: - *CVS-164529* --------- Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
…nvinotoolkit#29825) ### Details: Remove `-Warray-bounds` warning suppression flag, fix reported warnings ### Tickets: - N/A
…t#29274) MODEL_PTR proposal: openvinotoolkit#29107 Related PR: openvinotoolkit/openvino.genai#1915 CVS-163450
…kit#29442) ### Details: - *Gather node support mixed precision real16 to f32* - *Fuse precision convert to gather node in cpu plugin transformation* - *The convert in this pattern should be skipped in snippets tokenization* ### Tickets: - *CVS-163987*
… not load tokenizer using specified model ID or path. OpenVINO tokenizer/detokenizer models won't be generated. (openvinotoolkit#29397) ### Details: During test LLM models with NPU, I followed below configuration from [page](https://docs.openvino.ai/nightly/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html). However, I met below issue during convert the HF tokenizer to Openvino tokenizer. ```bash Could not load tokenizer using specified model ID or path. OpenVINO tokenizer/detokenizer models won't be generated. ``` After some test, we found the issue can be solved by update the optimum-intel to `1.22.0` and that's why I created a PR for this. Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> Co-authored-by: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
### Details: Add OV Transformation statistics doc file Fixed links ### Tickets: - *CVS-151320*
…inotoolkit#29839) ### Details: Amendment for openvinotoolkit#29817 Disable both batch1 and batch2 tests on ConvPoolReul_i32, since there are two failing tests. ### Tickets: - 164799
Add multiple Multiply pattern instead of Pow. ### Tickets: - *155289* --------- Signed-off-by: hyunback <hyunback.kim@intel.com>
sanleo-wq
requested review from
tsavina and
itikhono
and removed request for
a team
github-actions
bot
added
category: Core
github-actions
bot
added
category: CPU
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.
This fixes #29757
Implemented Tensor.setShape() in Node.js API
Updated TypeScript definitions in addon.ts
Added unit tests in tensor.test.js
Validated input parameters for setShape()
Changes:
Exposed ov::Tensor::set_shape method to JavaScript
Added setShape(shape: number[]) to Tensor interface
Implemented corresponding tests for different shape inputs