feat(vision-metrics): split vie_score

[davidberenstein1957]

Summary

Splits vie_score into its own stacked PR, adds VieScoreMetric, and wires GEditBench benchmark entry with focused VIE coverage.

Stack Position

• Base: PR feat(vision-metrics): split vqa #649 (feat/vlm-pr-4a-vqa)
• Next: PR feat(vision-metrics): split img_edit_score #651 (feat/vlm-pr-4c-img-edit-score)
• Final integration: PR feat(e2e-tests): stacked e2e after split metrics #641 (feat/vlm-pr-5-e2e-tests)
• Canonical umbrella reference: PR feat(evaluation): add VLMMetrics #545 (feat/metrics-vlm-support)

Files

• src/pruna/evaluation/metrics/metric_vie_score.py
• src/pruna/evaluation/benchmarks.py
• tests/evaluation/test_vision_metrics.py

Test Plan

uv run pytest tests/evaluation/test_vision_metrics.py -k vie_score

Review Focus

• VIE sub-score parsing/aggregation
• GEditBench wiring

Review Flow (Order)

Review the stack in this exact order:

1. feat(vendor): add LLM2Vec embedding model #637 vendor
2. feat(infrastructure): add VLM base classes and utilities #638 infrastructure
3. feat(text-metrics): split qa_accuracy #645 qa_accuracy
4. feat(text-metrics): split oneig_alignment #646 oneig_alignment
5. feat(text-metrics): split text_score pair #647 text_score pair
6. feat(text-metrics): split oneig_reasoning #648 oneig_reasoning
7. feat(vision-metrics): split vqa #649 vqa
8. feat(vision-metrics): split vie_score #650 vie_score
9. feat(vision-metrics): split img_edit_score #651 img_edit_score
10. feat(e2e-tests): stacked e2e after split metrics #641 e2e tests

This PR in the flow (8/10)

• Review after PR feat(vision-metrics): split vqa #649.
• Next PR to review: feat(vision-metrics): split img_edit_score #651.
• Confirm this PR's tests and scope before continuing.