Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add request envelope to support Multiserving frameworks #749

Merged
merged 91 commits into from
Nov 23, 2020

Conversation

abishekchiffon
Copy link
Contributor

@abishekchiffon abishekchiffon commented Oct 23, 2020

Description

Adds the wrapper feature to help Multiserving frameworks.
The envelope parses request from multiple Model serving frameworks like Seldon, KFServing, without any modifications in the handler code.
This PR builds on top of the PR #521 from Htappen

Type of change

Please delete options that are not relevant.

  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Feature/Issue validation/testing

-Additional units added to ts/torch_handler/unit_tests.
-Executed end to end flow and verified following
Gradle build logs :build_gradle_411_envelope.log
Unit test logs: unit_tests_411_envelope.log
Regression suite logs: regression_test_411_envelope.log

Checklist:

  • Have you added tests that prove your fix is effective or that this feature works?
  • New and existing unit tests pass locally with these changes?
  • Has code been commented, particularly in hard-to-understand areas?
  • Have you made corresponding changes to the documentation?

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-gpu
  • Commit ID: 5df8461
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@maaquib maaquib added this to the v0.3.0 milestone Nov 17, 2020
Copy link
Collaborator

@maaquib maaquib left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@abishekchiffon Seeing failures when running the unit test python -m pytest test_envelopes.py

========================================================================= short test summary info ==========================================================================
ERROR test_envelopes.py::test_json - RuntimeError: Missing the model.pt file
ERROR test_envelopes.py::test_json_batch - RuntimeError: Missing the model.pt file
ERROR test_envelopes.py::test_json_double_batch - RuntimeError: Missing the model.pt file
ERROR test_envelopes.py::test_body - RuntimeError: Missing the model.pt file
======================================================================= 1 passed, 4 errors in 0.55s ========================================================================

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-cpu
  • Commit ID: f427e5a
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-gpu
  • Commit ID: f427e5a
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-cpu
  • Commit ID: 63ba08f
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-gpu
  • Commit ID: 63ba08f
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-cpu
  • Commit ID: d20361e
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-gpu
  • Commit ID: d20361e
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@dhanainme dhanainme merged commit abcaf1a into pytorch:master Nov 23, 2020
@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-cpu
  • Commit ID: d20361e
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

@sagemaker-neo-ci-bot
Copy link
Collaborator

AWS CodeBuild CI Report

  • CodeBuild project: torch-serve-build-gpu
  • Commit ID: d20361e
  • Result: SUCCEEDED
  • Build Logs (available for 30 days)

Powered by github-codebuild-logs, available on the AWS Serverless Application Repository

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Add "RequestFormatter" config class to work with different inference platforms
9 participants