github-actions[bot] opened a new issue, #36640:
URL: https://github.com/apache/beam/issues/36640
Performance change found in the
test:
`pytorch_image_classification_benchmarks-resnet152-GPU-mean_load_model_latency_milli_secs`
for the metric: `mean_load_model_latency_milli_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?orgId=1&viewPanel=7
```
timestamp: Mon Oct 27 09:52:41 2025, metric_value: 108283.82
timestamp: Sun Oct 26 09:48:08 2025, metric_value: 116804.33
timestamp: Sat Oct 25 09:52:55 2025, metric_value: 110032.30
timestamp: Fri Oct 24 21:22:35 2025, metric_value: 114048.00 <---- Anomaly
timestamp: Fri Oct 24 13:50:52 2025, metric_value: 117670.75
timestamp: Fri Oct 24 02:55:17 2025, metric_value: 120804.62
timestamp: Thu Oct 9 00:55:35 2025, metric_value: 124572.40
timestamp: Fri Sep 12 09:35:29 2025, metric_value: 120755.78
timestamp: Thu Sep 11 10:09:23 2025, metric_value: 122038.18
timestamp: Wed Sep 10 09:57:38 2025, metric_value: 123256.57
timestamp: Tue Sep 9 09:32:55 2025, metric_value: 119402.92
timestamp: Mon Sep 8 09:35:29 2025, metric_value: 126086.77
timestamp: Sat Sep 6 09:26:53 2025, metric_value: 119414.80
timestamp: Thu Sep 4 09:53:11 2025, metric_value: 121251.18
```
--
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]
