[Feature] Split remote inference text list if its number exceeds user configured limitation #2455
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
Signed-off-by: Liyun Xiu <[email protected]>
chishui
requested review from
b4sjoo,
dhrubo-os,
jngz-es,
model-collapse,
rbhavna,
ylwu-amzn,
zane-neo,
Zhangxunmt,
austintlee,
HenryL27,
sam-herman and
xinyual
as code owners
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
Signed-off-by: Liyun Xiu <[email protected]>
chishui
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
chishui
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
chishui
temporarily deployed
to
ml-commons-cicd-env
GitHub Actions
Inactive
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
xinyual
reviewed
May 20, 2024
| } else { | ||
| // if the originalOrder is not empty, reorder based on it | ||
| List<ModelTensors> sortedModelTensors = Arrays.asList(new ModelTensors[modelTensorsList.size()]); | ||
| assert (originalOrderIndexes.size() == modelTensors.length); |
There was a problem hiding this comment.
I think the originalOrderIndexes size is the doc number, while modelTensors size is request size. So it would cause error. A simple way to reproduce is to try predict a four size input and set connector max batch size to 2. We may need to fetch all tensor and re-create ModelTensors Again.
One more small detail here: What is the list of modelTensors size here we want to keep? If we keep the size equal to request number, it may confuse user because actually sort and modelTensors is not the actual remote response (we re-sort it). So maybe keep all tensor into one modelTensors can be a choice.
There was a problem hiding this comment.
Thanks for catching this, it is a bug, will fix in next revision
Signed-off-by: Liyun Xiu <[email protected]>
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Failure
chishui
had a problem deploying
to
ml-commons-cicd-env
GitHub Actions
Error
ylwu-amzn
reviewed
May 20, 2024
| @@ -41,6 +45,9 @@ | |||
| import org.opensearch.script.ScriptService; | |||
|
|
|||
| public interface RemoteConnectorExecutor { | |||
| int DEFAULT_BATCH_SIZE = -1; | |||
| String MAX_BATCH_SIZE_KEY = "max_batch_size"; | |||
| String STEP_SIZE_KEY = "input_docs_processed_step_size"; | |||
There was a problem hiding this comment.
This one is to control the batch size , why need to add another variable max_batch_size ?
|
Will implement the logic from neural search side. Please refer to #2428 (comment) Closing now |
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.
Description
We'd like to have a solution to cut texts into small batches if total number of them in a batch request exceeds the limitation
Issues Resolved
#2428
Check List
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.