Add Dataflow GPU inference benchmark#6541
Open
piyush123 wants to merge 1 commit intoGoogleCloudPlatform:masterfrom
Open
Add Dataflow GPU inference benchmark#6541piyush123 wants to merge 1 commit intoGoogleCloudPlatform:masterfrom
piyush123 wants to merge 1 commit intoGoogleCloudPlatform:masterfrom
Conversation
Adds dpb_dataflow_gpu_inference_benchmark, a streaming benchmark that measures BERT text classification latency and throughput on Dataflow GPU workers. Compares two inference approaches across a configurable rate sweep: - local_gpu: model runs directly on the worker GPU via RunInference - vertex_ai: workers send HTTP requests to a Vertex AI endpoint Reports p50/p95/p99 latency, throughput, loss rate, and estimated cost per hour. Includes 27 unit tests.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds dpb_dataflow_gpu_inference_benchmark, a streaming benchmark that measures BERT text classification latency and throughput on Dataflow GPU workers. Compares two inference approaches across a configurable rate sweep:
Reports p50/p95/p99 latency, throughput, loss rate, and estimated cost per hour. Includes 27 unit tests.