SonicTriton: implement RetryActionDiffServer via TritonService; add tests and cfg support#22
Closed
trevin-lee wants to merge 1 commit intofastmachinelearning:masterfrom
Closed
Conversation
…end tests; add Catch2 unit test; update tritonTest_cfg.py for retry policy logging; ported to CMSSW_15_1_0_pre3 base
kpedro88
pushed a commit
that referenced
this pull request
Aug 25, 2025
|
@trevin-lee I've updated the master branch to synchronize with upstream cmssw now, but you may have to remake the PR (GitHub sometimes doesn't update correctly) |
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR description:
RetryActionDiffServerfor SonicTriton usingTritonService’s server registry; remove per-action alternate server parameters.TritonClient::updateServer(TritonService::Server::fallbackName)to switch servers on retry, per review guidance.HeterogeneousCore/SonicTriton/test/test_RetryActionDiffServer.cc(arms → updateServer(fallback) → no-op on second retry → exception path is caught).HeterogeneousCore/SonicTriton/test/tritonTest_cfg.pywith--retryAction {same,diff}and a verbose confirmation line.TestHeterogeneousCoreSonicTritonRetryActionDiff_Logto assert the selected retry policy.HeterogeneousCore/SonicTriton/test/BuildFile.xml(remove package-level test entries; use proper<bin>withcatch2).TritonClient(test double support), removing the unused testing flag constructor.PR validation:
CMSSW_15_1_0_pre3area:scram b -j 8scram b runtests TEST=HeterogeneousCore/SonicTriton(passes)sameanddiffpolicies.Client.Retryis explicitly configured.Backport:
CMSSW_15_0_Xafter this PR is reviewed.