Skip to content

[release_v300] Bump openvino RC 2026.0.0 #3869

Merged
AlexanderDokuchaev merged 11 commits into
openvinotoolkit:release_v300from
AlexanderDokuchaev:r300/bump_ov_rc
Feb 6, 2026
Merged

[release_v300] Bump openvino RC 2026.0.0 #3869
AlexanderDokuchaev merged 11 commits into
openvinotoolkit:release_v300from
AlexanderDokuchaev:r300/bump_ov_rc

Conversation

@AlexanderDokuchaev
Copy link
Copy Markdown
Collaborator

@AlexanderDokuchaev AlexanderDokuchaev commented Jan 30, 2026

@github-actions github-actions Bot added documentation Improvements or additions to documentation NNCF PT Pull requests that updates NNCF PyTorch NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF ONNX Pull requests that updates NNCF ONNX release target NNCF PTQ Pull requests that updates NNCF PTQ labels Jan 30, 2026
AlexanderDokuchaev and others added 7 commits January 30, 2026 17:41
…notoolkit#3885)

### Changes

Fix the `compress_quantize_weights_transformation()` method by removing
names of removed initializers from graph inputs.
…3889)

### Changes

- Fix incorrect insertion of MatMulNBits nodes
- Use lazy creation of `onnx.utils.Extractor` object

### Reason for changes

Weight Compression tests failed with openvino 2026.0.0rc2
@AlexanderDokuchaev AlexanderDokuchaev changed the title Bump openvino RC 2026.0.0 [release_v300] Bump openvino RC 2026.0.0 Feb 6, 2026
AlexanderDokuchaev and others added 2 commits February 6, 2026 11:01
### Changes

Rewrite codebook values in weight compression config for adaptive
codebook per-layer.

### Reason for changes

Better accuracy:
llama3.2_1b_fix, gen_kwargs: (None), limit: None, num_fewshot: None,
batch_size: 4
```
|    Tasks     |Version|Filter|n-shot|  Metric  |   |Value |   |Stderr|
|--------------|------:|------|-----:|----------|---|-----:|---|-----:|
|lambada_openai|      1|none  |     0|acc       |↑  |0.5766|±  |0.0069|
|              |       |none  |     0|perplexity|↓  |7.6888|±  |0.2334|
```


llama3.2_1b_develop), gen_kwargs: (None), limit: None, num_fewshot:
None, batch_size: 4
```
|    Tasks     |Version|Filter|n-shot|  Metric  |   |Value |   |Stderr|
|--------------|------:|------|-----:|----------|---|-----:|---|-----:|
|lambada_openai|      1|none  |     0|acc       |↑  |0.5496|±  |0.0069|
|              |       |none  |     0|perplexity|↓  |8.5684|±  |0.2661|
```


### Related tickets


### Tests
https://github.com/openvinotoolkit/nncf/actions/runs/21712541469

---------

Co-authored-by: Aleksandr Suslov <alexander.suslov@intel.com>
@AlexanderDokuchaev AlexanderDokuchaev marked this pull request as ready for review February 6, 2026 10:02
@AlexanderDokuchaev AlexanderDokuchaev requested a review from a team as a code owner February 6, 2026 10:02
@AlexanderDokuchaev AlexanderDokuchaev merged commit 91e6e3f into openvinotoolkit:release_v300 Feb 6, 2026
22 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation NNCF ONNX Pull requests that updates NNCF ONNX NNCF OpenVINO Pull requests that updates NNCF OpenVINO NNCF PT Pull requests that updates NNCF PyTorch NNCF PTQ Pull requests that updates NNCF PTQ release target

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants