github-actions[bot] opened a new issue, #39910:
URL: https://github.com/apache/beam/issues/39910
Performance change found in the
test:
`pytorch_image_classification_benchmarks-resnet152-GPU-mean_inference_batch_latency_micro_secs`
for the metric: `mean_inference_batch_latency_micro_secs`.
For more information on how to triage the alerts, please look at
`Triage performance alert issues` section of the
[README](https://github.com/apache/beam/tree/master/sdks/python/apache_beam/testing/analyzers/README.md#triage-performance-alert-issues).
`Test description:` Pytorch image classification on 50k images of size 224 x
224 with resnet 152 with Tesla T4 GPU.
Test link -
https://github.com/apache/beam/blob/42d0a6e3564d8b9c5d912428a6de18fb22a13ac1/.test-infra/jenkins/job_InferenceBenchmarkTests_Python.groovy#L151).
Test dashboard -
http://metrics.beam.apache.org/d/ZpS8Uf44z/python-ml-runinference-benchmarks?from=now-90d&to=now&viewPanel=2
```
timestamp: Thu Aug 27 11:48:37 2026, metric_value: 213343.97
timestamp: Wed Aug 26 09:48:29 2026, metric_value: 213814.14
timestamp: Tue Aug 25 09:54:08 2026, metric_value: 226941.91 <---- Anomaly
timestamp: Mon Aug 24 09:44:37 2026, metric_value: 163499.59
timestamp: Sun Aug 23 09:56:45 2026, metric_value: 179909.68
timestamp: Sat Aug 22 09:44:34 2026, metric_value: 215017.68
timestamp: Fri Aug 21 09:38:25 2026, metric_value: 145019.75
timestamp: Thu Aug 20 09:39:07 2026, metric_value: 148610.39
timestamp: Wed Aug 19 09:46:00 2026, metric_value: 165965.24
timestamp: Tue Aug 18 10:17:01 2026, metric_value: 145126.27
timestamp: Mon Aug 17 10:31:52 2026, metric_value: 164313.68
timestamp: Sun Aug 16 10:14:23 2026, metric_value: 141771.83
timestamp: Sat Aug 15 09:54:48 2026, metric_value: 168590.23
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
