Azure / Azure/MachineLearningNotebooks
increase scoring_timeout_ms
- Dominant language
- Jupyter Notebook
- Stars
- 4.4k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
the "scoring_time_out" has currently a max_limit of 300000 [ms]. Is it possible to increase that further? I created a WebService which trains models based on our Lab Data etc.. And for some products/materials the modelling will take more that 300s. Or is there a way to "bypass" the scoring_timeout_ms?
service = Webservice(name="ModellingWebService", workspace=ws)
service.update( inference_config=inference_config,
autoscale_enabled = True,
autoscale_target_utilization=50,
autoscale_min_replicas=1,
autoscale_max_replicas=10,
cpu_cores = 1,
cpu_cores_limit=6,
memory_gb = 3,
memory_gb_limit=20,
scoring_timeout_ms = 300000, #max 300s or update fails
max_request_wait_time = 15000)
Grüße
Marvin
---
#### Document Details
⚠ *Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.*
* ID: 2b1a7ca9-d49f-d32c-8b43-3e8fc9576815
* Version Independent ID: bc09c6bb-e989-14e6-5ab4-06a1fcd2f3a1
* Content: [azureml.core.webservice.aks.AksWebservice class - Azure Machine Learning Python](https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.webservice.aks.akswebservice?view=azure-ml-py)
* Content Source: [AzureML-Docset/stable/docs-ref-autogen/azureml-core/azureml.core.webservice.aks.AksWebservice.yml](https://github.com/MicrosoftDocs/MachineLearning-Python-pr/blob/live/AzureML-Docset/stable/docs-ref-autogen/azureml-core/azureml.core.webservice.aks.AksWebservice.yml)
* Service: **machine-learning**
* Sub-service: **core**
* GitHub Login: @DebFro
* Microsoft Alias: **debfro**
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.