github-actions[bot] opened a new issue, #36057:
URL: https://github.com/apache/beam/issues/36057
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 Sep 4 09:53:11 2025, metric_value: 155773.41
timestamp: Wed Sep 3 09:39:32 2025, metric_value: 140479.62
timestamp: Tue Sep 2 09:42:36 2025, metric_value: 155039.58 <---- Anomaly
timestamp: Mon Sep 1 09:37:56 2025, metric_value: 120460.40
timestamp: Sun Aug 31 09:43:01 2025, metric_value: 107916.67
timestamp: Sat Aug 30 09:37:33 2025, metric_value: 114573.30
timestamp: Fri Aug 29 09:58:20 2025, metric_value: 108389.14
timestamp: Thu Aug 28 09:32:31 2025, metric_value: 109742.37
timestamp: Wed Aug 27 09:52:55 2025, metric_value: 113383.06
timestamp: Tue Aug 26 10:06:53 2025, metric_value: 112406.15
timestamp: Mon Aug 25 10:19:50 2025, metric_value: 112465.75
timestamp: Sun Aug 24 09:56:22 2025, metric_value: 124457.02
timestamp: Fri Aug 22 10:16:29 2025, metric_value: 108742.54
```
--
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]
