Streaming Model API #13
Draft
Conversation
This file contains 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
added 7 commits
July 29, 2020 19:19
added 10 commits
August 6, 2020 21:50
Benchmarks showed that TagByOperation was a performance bottleneck* as it requires disc access per query batch. To mitigate this I implemented operation caching inside the DoFn. For readability, I also renamed this operation to "SplitByOperation" as that more accurately describes its purpose. On a dataset with 1m examples, TagByOperation took ~25% of the total wall time. After implementing caching, this was reduced to ~2%.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Streaming Model API
This PR introduces a streaming model API for
RunInference.Overview
In addition to the current api:
It is now possible to use a PCollection of inference_spec_type as a side input or run inference on queries directly:
Notes
This PR depends on #11 and #12
This PR introduces
beam.GroupIntoBatchesand_TemporalJoinwhich both require stateful DoFn support. This is not supported in Dataflow v1 and currentlyRunInferenceis broken in Dataflow v2 due to BEAM-2717