Skip to content

Conversation

@pskiran1
Copy link
Member

@pskiran1 pskiran1 commented Dec 1, 2025

What does the PR do?

This PR includes comprehensive test coverage to verify that the model ready status accurately reflects the health of the underlying stub process.

Key changes:

  • Added a new test suite to verify model ready checks detect crashed stub processes
  • Tests simulate process failures using different signals (SIGSEGV and SIGKILL)
  • Validates both HTTP and gRPC endpoints report correct model readiness status

Checklist

  • PR title reflects the change and is of format <commit_type>: <Title>
  • Changes are described in the pull request.
  • Related issues are referenced.
  • Populated github labels field
  • Added test plan and verified test passes.
  • Verified that the PR passes existing CI.
  • Verified copyright is correct on all changed files.
  • Added succinct git squash message before merging ref.
  • All template sections are filled out.
  • Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

  • build
  • ci
  • docs
  • feat
  • fix
  • perf
  • refactor
  • revert
  • style
  • test

Related PRs:

Where should the reviewer start?

Test plan:

  • CI Pipeline ID: 39870794

Caveats:

Background

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

  • closes GitHub issue: #xxx

@pskiran1 pskiran1 requested a review from Copilot December 2, 2025 16:23
Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR adds functionality to detect when a Python backend stub process becomes unresponsive or crashes. The implementation includes comprehensive test coverage to verify that the model ready status accurately reflects the health of the underlying stub process.

Key changes:

  • Added a new test suite to verify model ready checks detect crashed stub processes
  • Tests simulate process failures using different signals (SIGSEGV and SIGKILL)
  • Validates both HTTP and gRPC endpoints report correct model readiness status

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.

File Description
qa/L0_backend_python/test.sh Adds new model_ready_check test to the test suite execution
qa/L0_backend_python/model_ready_check/test.sh Test script that simulates stub process crashes and verifies model ready status
qa/L0_backend_python/model_ready_check/check_model_ready.py Python test cases for checking model ready status via HTTP and gRPC

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@pskiran1 pskiran1 added the PR: ci Changes to our CI configuration files and scripts label Dec 5, 2025
@pskiran1 pskiran1 changed the title fix: Enable detection of unresponsive or crashed Python backend stub process ci: Enable detection of unresponsive or crashed Python backend stub process Dec 5, 2025
@pskiran1 pskiran1 marked this pull request as ready for review December 5, 2025 16:36
whoisj
whoisj previously approved these changes Dec 5, 2025
@pskiran1 pskiran1 requested a review from yinggeh December 8, 2025 04:34
yinggeh
yinggeh previously approved these changes Dec 8, 2025
@pskiran1 pskiran1 dismissed stale reviews from yinggeh and whoisj via 0b29cb4 December 8, 2025 08:31
yinggeh
yinggeh previously approved these changes Dec 8, 2025
@pskiran1 pskiran1 requested a review from yinggeh December 8, 2025 13:13
@yinggeh
Copy link
Contributor

yinggeh commented Dec 8, 2025

Please also document in backend/README.md of the new CAPI TRITONBACKEND_ModelInstanceReady

@pskiran1 pskiran1 merged commit 97f2f46 into main Dec 9, 2025
3 checks passed
@pskiran1 pskiran1 deleted the spolisetty/tri-231-backend-endpoint-reports-to-be-healthy-when-using branch December 9, 2025 12:48
mc-nv pushed a commit that referenced this pull request Dec 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

PR: ci Changes to our CI configuration files and scripts

Development

Successfully merging this pull request may close these issues.

4 participants