[ORT GPU][WebNN] Fail to run two WebNN batchNormalization tests due to tolerance issues

[BruceDai]

Describe the issue

Fail to run below two WebNN batchNormalization tests due to tolerance issues by ORT default GPU EP.

Test	Error message
batchNormalization float32 2D constant tensors default options	assert_less_than_equal: assert_array_approx_equals_ulp: test batchNormalization float32 actual 1.8526287078857422 should be close enough to expected 1.8526301383972168 by ULP distance: expected a number less than or equal to 6n but got 12n
batchNormalization options.axis=0 + gelu	assert_less_than_equal: assert_array_approx_equals_ulp: test batchNormalization gelu float32 actual -0.035951320081949234 should be close enough to expected -0.03595117852091789 by ULP distance: expected a number less than or equal to 24n but got 38n

/cc @fdwr PTAL, thanks!

To reproduce

1. Install Windows App SDK Stable 1.8.2 (1.8.251003001)
2. Install lates Edge Canary browser
3. Launch Edge Canary browser, navigate to about://flags enabled "Enables WebNN API" and "ONNX Runtime backend for WebNN" flags, then relaunch browser
4. Run each failure test using below test url

Test	Test URL
batchNormalization float32 2D constant tensors default options	https://wpt.live/webnn/conformance_tests/batch_normalization.https.any.html?device=gpu&tc=batchNormalization%20float32%202D%20constant%20tensors%20default%20options
batchNormalization options.axis=0 + gelu	https://wpt.live/webnn/conformance_tests/subgraph.https.any.html?device=gpu&tc=batchNormalization%20options.axis=0%20%2B%20gelu

Urgency

No response

ONNX Runtime Installation

Released Package Windows App SDK Stable 1.8.2 (1.8.251003001)

ONNX Runtime Version or Commit ID

1.23.25.928

Execution Provider

ORT default GPU EP