Skip to content

fix(trainer): preserve local job runtime metadata #657

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.

Sign up for GitHub

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

Open
lntutor wants to merge 1 commit into
base: main
Choose a base branch
from
+23 −1
Open

fix(trainer): preserve local job runtime metadata #657

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion kubeflow/trainer/backends/localprocess/backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,7 +156,7 @@ def list_jobs(self, runtime: types.Runtime | None = None) -> list[types.TrainJob
types.TrainJob(
name=_job.name,
creation_timestamp=_job.created,
runtime=runtime,
runtime=_job.runtime,
num_nodes=1,
steps=[
types.Step(name=s.step_name, pod_name=s.step_name, status=s.job.status)
Expand Down
22 changes: 22 additions & 0 deletions kubeflow/trainer/backends/localprocess/backend_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -411,6 +411,28 @@ def test_list_jobs(local_backend, test_case):
assert isinstance(jobs, list)


def test_list_jobs_without_runtime_filter_preserves_stored_runtime(
local_backend, mock_train_environment
):
"""Test unfiltered job listings retain each job's runtime metadata."""
runtime = types.Runtime(
name=TORCH_RUNTIME,
trainer=types.RuntimeTrainer(
trainer_type=types.TrainerType.CUSTOM_TRAINER,
framework="torch",
image=LOCAL_RUNTIME_IMAGE,
),
kind=types.RuntimeKind.TRAINING_RUNTIME,
)

local_backend.train(runtime=runtime, trainer=types.CustomTrainer(func=dummy_training_function))

jobs = local_backend.list_jobs()

assert len(jobs) == 1
assert jobs[0].runtime == runtime


@pytest.mark.parametrize(
"test_case",
[
Expand Down