feat: support batch inference #3099
Closed
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
Codecov Report
@@ Coverage Diff @@
## main #3099 +/- ##
==========================================
- Coverage 33.45% 32.90% -0.55%
==========================================
Files 106 132 +26
Lines 9769 10652 +883
Branches 1685 1771 +86
==========================================
+ Hits 3268 3505 +237
- Misses 6270 6914 +644
- Partials 231 233 +2
|
5 tasks
|
ah next time you can also do a |
aarnphm
reviewed
Oct 15, 2022
| @@ -0,0 +1,193 @@ | |||
| from __future__ import annotations | |||
There was a problem hiding this comment.
Should this be under src/bentoml/_internal/distributed/spark.py? @sauyon
There was a problem hiding this comment.
Maybe batch, but it doesn't really matter right now.
Co-authored-by: Quan Nguyen <quandollar@users.noreply.github.com>
Co-authored-by: Quan Nguyen <quandollar@users.noreply.github.com>
aarnphm
reviewed
Oct 20, 2022
examples/batch_processing/service.py
Outdated
Comment on lines
10
to
22
| @svc.api( | ||
| input=PandasDataFrame(), | ||
| output=PandasSeries(dtype="float"), | ||
| ) | ||
| async def classify1(input_series: pd.DataFrame) -> pd.Series: | ||
| return await PandasDataFrame(iris_clf_runner.predict.async_run(input_series)) | ||
|
|
||
| @svc.api( | ||
| input=PandasSeries(), | ||
| output=PandasSeries(), | ||
| ) | ||
| async def classify2(input_series: pd.Series) -> pd.Series: | ||
| return await PandasSeries(iris_clf_runner.predict.async_run(input_series)) |
There was a problem hiding this comment.
nit: let sname the endpoint something more helpful.
aarnphm
reviewed
Oct 20, 2022
|
Development now track at #3425 |
|
Awesome work on this one 🎉 |
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.
What does this PR address?
BentoML supports serving models online through HTTP and gRPC but needs more support for batch and streaming inference. Integrating with Apache Spark helps bridge the gap. This PR involves allowing users to create Spark UDFs with BentoML-packaged ML models in different types of environment.
Fixes #890
Before submitting:
guide on how to create a pull request.
make formatandmake lintscript have passed (instructions)?those accordingly? Here are documentation guidelines and tips on writting docs.