Add max_num_iterations parameter for accuracy-aware quantization

[A-Artemis]

Summary

Adds a NumberField to the quantization options for the new parameter, and accepts the new parameter on the backend.

Checklist

• The PR title and description are clear and descriptive
• I have manually tested the changes
• All changes are covered by automated tests
• All related issues are linked to this PR (if applicable)
• Documentation has been updated (if applicable)

[jpggvilaca]

UI lgtm

[github-actions]

📊 Test coverage report

Metric	Coverage
Lines	60.2%
Functions	56.8%
Branches	51.8%
Statements	59.8%

[github-actions]

🐳 Docker image sizes

Device	Size
xpu	10801.7 MB (10.55 GB)
cpu	4013.1 MB (3.92 GB)
cuda	10208.3 MB (9.97 GB)

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

❌ Patch coverage is 40.00000% with 3 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
...brary/src/getitune/backend/openvino/models/base.py	0.00%	3 Missing ⚠️

📢 Thoughts on this report? Let us know!

[github-actions]

⏱️ Backend import time — app.main

Accelerator	Cumulative (s)	Self (s)
cpu	5.082	0.004
cuda	4.121	0.003
xpu	4.624	0.003

[Copilot]

Pull request overview

Adds support for configuring max_num_iterations for accuracy-aware quantization end-to-end (UI → backend job API → GetiTune/OpenVINO quantization), wiring it into NNCF’s advanced accuracy restorer settings and expanding test coverage across components.

Changes:

• Library: extend OV PTQ optimization to accept max_num_iterations and translate it into NNCF AdvancedAccuracyRestorerParameters for accuracy-aware PTQ.
• Backend: accept/propagate max_num_iterations through quantization job request/params/execution and include it in job metadata.
• UI: add a new quantization dialog field and extend Playwright tests to validate the new parameter is submitted.

Reviewed changes

Copilot reviewed 13 out of 13 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
library/tests/unit/backend/openvino/test_engine.py	Adds unit assertions for max_num_iterations handling in PTQ config.
library/src/getitune/backend/openvino/models/base.py	Pops max_num_iterations and maps it to NNCF advanced accuracy restorer parameters.
library/src/getitune/backend/openvino/engine.py	Extends OVEngine.optimize() API to accept and forward max_num_iterations.
application/ui/tests/models/models-page.ts	Adds page object accessor for the new iterations input.
application/ui/tests/models/model-details.spec.ts	Extends UI test to submit/verify max_num_iterations in quantization job payload.
application/ui/src/features/models/model-listing/model-variants/quantization-dialog/quantization-fields.component.tsx	Adds the new “Max number of iterations” field and default parameter.
application/ui/src/features/models/model-listing/model-variants/quantization-dialog/quantization-dialog.component.tsx	Wires the new UI state into the quantize job request body.
application/backend/tests/unit/execution/quantization/test_getitune_quantizer.py	Extends unit tests to assert propagation of max_num_iterations.
application/backend/tests/unit/api/routers/test_jobs.py	Extends router tests to include/validate the new parameter.
application/backend/app/models/jobs/quantization_job.py	Adds max_num_iterations to quantization job params model.
application/backend/app/execution/quantization/getitune_quantizer.py	Propagates max_num_iterations through quantization execution into OVEngine.
application/backend/app/api/schemas/jobs/quantization.py	Adds request and metadata schema support for max_num_iterations.
application/backend/app/api/routers/jobs.py	Passes the new parameter when creating quantization jobs.