[air](deps): Bump torchmetrics from 0.10.3 to 1.9.0 in /python/requirements/ml

[dependabot]

Bumps torchmetrics from 0.10.3 to 1.9.0.

Release notes

Sourced from torchmetrics's releases.

Release v1.9.0

[1.9.0] - 2026-03-06

Changed

• Defaulting Dice score average="macro" (#3042)
• Dropped Python 3.9 support, set 3.10 as minimum (#3330)
• Replaced pkg_resources with packaging (#3329)

Fixed

• Fixed device mismatch in Metric base class (#3316)
• Fixed n-d slicing deprecation warning (#3319)
• Fixed tensor copy warning in logAUC (#3295)
• Fixed memory issues when computing retrieval metrics with high-valued indices (#3291)
• Fixed race condition in _safe_divide by creating tensor directly on device (#3284)

---

Key Contributors

@​adaliaramon, @​bhimrazy, @​GdoongMathew, @​Isalia20, @​KyleMylonakisProtopia, @​VijayVignesh1

New Contributors

• @​PussyCat0700 made their first contribution in Lightning-AI/torchmetrics#3182
• @​iamkulbhushansingh made their first contribution in Lightning-AI/torchmetrics#3196
• @​adosar made their first contribution in Lightning-AI/torchmetrics#3282
• @​bhimrazy made their first contribution in Lightning-AI/torchmetrics#3306
• @​VijayVignesh1 made their first contribution in Lightning-AI/torchmetrics#3295
• @​KyleMylonakisProtopia made their first contribution in Lightning-AI/torchmetrics#3319
• @​GdoongMathew made their first contribution in Lightning-AI/torchmetrics#3316
• @​adaliaramon made their first contribution in Lightning-AI/torchmetrics#3291

If we forgot someone due to not matching commit email with GitHub account, let us know :]

---

Full Changelog: Lightning-AI/torchmetrics@v1.8.0...v1.9.0

Minor patch release

[1.8.2] - 2025-09-03

Fixed

• Fixed BinaryPrecisionRecallCurve now returns NaN for precision when no predictions meet a threshold (#3227)
• Fixed precision_at_fixed_recall and recall_at_fixed_precision to correctly return NaN thresholds when recall/precision conditions are not met (#3226)

---

... (truncated)

Changelog

Sourced from torchmetrics's changelog.

[1.9.0] - 2026-03-05

Changed

• Defaulting Dice score average="macro" (#3042)
• Dropped Python 3.9 support, set 3.10 as minimum (#3330)
• Replaced pkg_resources with packaging (#3329)

Fixed

• Fixed device mismatch in Metric base class (#3316)
• Fixed n-d slicing deprecation warning (#3319)
• Fixed tensor copy warning in logAUC (#3295)
• Fixed memory issues when computing retrieval metrics with high-valued indices (#3291)
• Fixed race condition in _safe_divide by creating tensor directly on device (#3284)

[1.8.2] - 2025-09-03

Fixed

• Fixed BinaryPrecisionRecallCurve now returns NaN for precision when no predictions meet a threshold (#3227)
• Fixed precision_at_fixed_recall and recall_at_fixed_precision to correctly return NaN thresholds when recall/precision conditions are not met (#3226)

[1.8.1] - 2025-08-07

Changed

• Added reduction='none' to vif metric (#3196)
• Float input support for segmentation metrics (#3198)

Fixed

• Fixed unintended sigmoid normalization in BinaryPrecisionRecallCurve (#3182)

[1.8.0] - 2025-07-23

Added

• Added VMAF metric to new video domain (#2991)
• Added CRPS in regression domain (#3024)
• Added aggregation_level argument to DiceScore (#3018)
• Added support for reduction="none" to LearnedPerceptualImagePatchSimilarity (#3053)
• Added support single str input for functional interface of bert_score (#3056)
• Enhance: BERTScore to evaluate hypotheses against multiple references (#3069)
• Added Lip Vertex Error (LVE) in multimodal domain (#3090)
• Added antialias argument to FID metric (#3177)
• Added mixed input format to segmentation metrics (#3176)

... (truncated)

Commits

• 700261d Refactor GitHub Actions for PyPI publishing (#3334)
• 2ec81e6 chore: update changelog & version for 1.9.0 (#3332)
• 32f3e01 Fix race condition in _safe_divide by creating tensor directly on device (#...
• 76d4262 Fix memory issues when computing retrieval metrics with high-valued indices (...
• 8e1b7b3 chore: drop Python 3.9, set 3.10 as minimum (#3330)
• 4d52812 fix device mismatch (#3316)
• 41506c3 Docs: fix math blocks (#3325)
• 18bd245 fix: replace pkg_resources with packaging and pin setuptools <82.0.0 (#3329)
• bfcc276 Fix EER docstrings (#3312)
• 52ea730 fix: add tuple cast to avoid nd slicing deprecation warning (#3319)
• Additional commits viewable in compare view

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 commands and options

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 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)