MLA-C01 · Question #153
A company has an existing Amazon SageMaker model (v1) on a production endpoint. The company develops a new model version (v2) and needs to test v2 in production before substituting v2 for v1. The…
The correct answer is D. Deploy v2 into a shadow variant that samples 100% of the inference requests. Collect all the. A shadow variant allows the new model (v2) to receive a copy of 100% of production traffic while only v1’s outputs are returned to users. This enables safe side-by-side evaluation of v2 without impacting production responses, minimizing risk and ensuring no disruption of live…
Question
A company has an existing Amazon SageMaker model (v1) on a production endpoint. The company develops a new model version (v2) and needs to test v2 in production before substituting v2 for v1. The company needs to implement a solution to minimize the risk of v2 generating incorrect output in production. The solution must prevent any disruption of production traffic during the change to v2. Which solution will meet these requirements?
Options
- ACreate a second production variant for v2. Assign 1% of the traffic to v2 and 99% of the traffic to
- BCreate a second production variant for v2. Assign 10% of the traffic to v2 and 90% of the traffic to
- CDeploy v2 to a new endpoint. Turn on data capturing for the production endpoint. Write a script to
- DDeploy v2 into a shadow variant that samples 100% of the inference requests. Collect all the
How the community answered
(26 responses)- A19% (5)
- B8% (2)
- C4% (1)
- D69% (18)
Explanation
A shadow variant allows the new model (v2) to receive a copy of 100% of production traffic while only v1’s outputs are returned to users. This enables safe side-by-side evaluation of v2 without impacting production responses, minimizing risk and ensuring no disruption of live traffic until v2 is validated and promoted.
Topics
Community Discussion
No community discussion yet for this question.