Skip to content

Commit

Permalink
Merge pull request #188 from TaekyungHeo/k8s-nccl-report-bugfix
Browse files Browse the repository at this point in the history
Fix bug in generating NCCL test reports on K8s
  • Loading branch information
TaekyungHeo committed Sep 10, 2024
2 parents d96c0b6 + 9b57912 commit 03c23d6
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 1 deletion.
4 changes: 3 additions & 1 deletion src/cloudai/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,9 @@

Registry().add_strategy(InstallStrategy, [SlurmSystem], [NcclTest], NcclTestSlurmInstallStrategy)
Registry().add_strategy(InstallStrategy, [SlurmSystem], [NeMoLauncher], NeMoLauncherSlurmInstallStrategy)
Registry().add_strategy(ReportGenerationStrategy, [SlurmSystem], [NcclTest], NcclTestReportGenerationStrategy)
Registry().add_strategy(
ReportGenerationStrategy, [SlurmSystem, KubernetesSystem], [NcclTest], NcclTestReportGenerationStrategy
)
Registry().add_strategy(CommandGenStrategy, [StandaloneSystem], [Sleep], SleepStandaloneCommandGenStrategy)
Registry().add_strategy(CommandGenStrategy, [SlurmSystem], [Sleep], SleepSlurmCommandGenStrategy)
Registry().add_strategy(JsonGenStrategy, [KubernetesSystem], [Sleep], SleepKubernetesJsonGenStrategy)
Expand Down
1 change: 1 addition & 0 deletions tests/test_init.py
Original file line number Diff line number Diff line change
Expand Up @@ -120,6 +120,7 @@ def test_runners():
((ReportGenerationStrategy, SlurmSystem, ChakraReplay), ChakraReplayReportGenerationStrategy),
((ReportGenerationStrategy, SlurmSystem, JaxToolbox), JaxToolboxReportGenerationStrategy),
((ReportGenerationStrategy, SlurmSystem, NcclTest), NcclTestReportGenerationStrategy),
((ReportGenerationStrategy, KubernetesSystem, NcclTest), NcclTestReportGenerationStrategy),
((ReportGenerationStrategy, SlurmSystem, NeMoLauncher), NeMoLauncherReportGenerationStrategy),
((ReportGenerationStrategy, SlurmSystem, Sleep), SleepReportGenerationStrategy),
((ReportGenerationStrategy, SlurmSystem, UCCTest), UCCTestReportGenerationStrategy),
Expand Down

0 comments on commit 03c23d6

Please sign in to comment.