ExamTopics Logo
Mail Us[email protected]
Menu
Microsoft Discussions
exam questions

Exam DP-100 All Questions

View all questions & answers for the DP-100 exam
Go to Exam

Exam DP-100 topic 4 question 13 discussion

Actual exam question from Microsoft's DP-100
Question #: 13
Topic #: 4
[All DP-100 Questions]

You use Azure Machine Learning designer to create a real-time service endpoint. You have a single Azure Machine Learning service compute resource.
You train the model and prepare the real-time pipeline for deployment.
You need to publish the inference pipeline as a web service.
Which compute type should you use?

  • A. a new Machine Learning Compute resource
  • B. Azure Kubernetes Services
  • C. HDInsight
  • D. the existing Machine Learning Compute resource
  • E. Azure Databricks
Show Suggested Answer Hide Answer
Suggested Answer: B 🗳️
by ZeeshanNawaz at Feb. 11, 2021, 1:06 a.m.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
ljljljlj
Highly Voted 2 years, 11 months ago
On exam 2021/7/10
upvoted 7 times
...
james2033
Most Recent 8 months ago
Selected Answer: B
B, for deployment phase, AKS. Not powerful computer for training model.
upvoted 1 times
...
phdykd
1 year, 3 months ago
D. the existing Machine Learning Compute resource Since you already have a single Azure Machine Learning service compute resource, it is recommended to use it to publish the inference pipeline as a web service. This will help you to minimize the cost and simplify the deployment process.
upvoted 2 times
...
michaelmorar
1 year, 6 months ago
Selected Answer: B
AKS always the solution for these types of problems.
upvoted 3 times
...
[Removed]
2 years, 3 months ago
On 20Feb2022
upvoted 1 times
...
andre999
2 years, 12 months ago
The answer is correct: Azure Kubernetes Service (AKS) is used for Real-time inference.
upvoted 4 times
...
Lucario95
3 years, 1 month ago
Doesn't the question refer to which compute to use to deploy the pipeline, thus answer D being correct?
upvoted 1 times
azure1000
2 years, 10 months ago
It says you need to publish the model, thus Aks
upvoted 2 times
...
...
ZeeshanNawaz
3 years, 4 months ago
Why the existing compute can't be used?
upvoted 1 times
Zwi3b3l
3 years, 3 months ago
As per https://docs.microsoft.com/en-us/azure/machine-learning/concept-compute-target only AKS can be used for real-time interference
upvoted 6 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel