cortexgrid 0.3.12__tar.gz → 0.3.14__tar.gz

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: cortexgrid
-Version: 0.3.12
+Version: 0.3.14
 Summary: Connect your ML code to the RoboLab compute cluster — Ray, MLflow, and S3
 Project-URL: Homepage, https://github.com/robodatalab/cortexgrid
 Project-URL: Repository, https://github.com/robodatalab/cortexgrid

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/cortexgrid/__init__.py

@@ -35,6 +35,7 @@ from cortexgrid import state
 from cortexgrid.checkpoint import checkpoint, resume
 from cortexgrid.experiment import (
     Experiment,
+    active_experiment,
     delete_experiment,
     delete_run,
     list_experiments,
@@ -107,13 +108,13 @@ from cortexgrid.model_serving import (
     ModelNotDeployed,
     ModelRequirements,
     ServingStatus,
-    deploy_model,
     list_deployed_models,
     model_serving_status,
     redeploy_model,
     undeploy_model,
     wait_for_model_serving,
 )
+from cortexgrid.model_serving import deploy_model as _deploy_model_serving
 
 
 def remote(
@@ -227,6 +228,28 @@ def register_model(
     return model
 
 
+def deploy_model(
+    family: str,
+    suffix: str,
+    run_name: str,
+    num_replicas: int = 1,
+    wait: bool = False,
+    timeout: float | None = 300.0,
+    config: DeploymentConfig | None = None,
+) -> Deployment:
+    experiment = active_experiment()
+    return _deploy_model_serving(
+        family,
+        suffix,
+        run_name,
+        num_replicas=num_replicas,
+        wait=wait,
+        timeout=timeout,
+        config=config,
+        experiment_name="" if experiment is None else experiment.experiment_name,
+    )
+
+
 def _record_imported_model(
     run_id: str, family: str, suffix: str, model: SavedModel
 ) -> None:

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/cortexgrid/experiment.py

@@ -104,6 +104,10 @@ class Experiment:
         set_instance(None)
 
 
+def active_experiment() -> Experiment | None:
+    return _SINGLETON_EXPERIMENT
+
+
 def set_instance(instance: Experiment | None) -> None:
     global _SINGLETON_EXPERIMENT
     _SINGLETON_EXPERIMENT = instance

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/cortexgrid/jobs.py

@@ -29,7 +29,7 @@ from pydantic import BaseModel, ConfigDict
 log = logging.getLogger(__name__)
 
 _JOB_POLL_INTERVAL_S = 5.0
-_TERMINAL_JOB_STATES = (JobStatus.FINISHED, JobStatus.FAILED, JobStatus.STOPPED)
+TERMINAL_JOB_STATES = (JobStatus.FINISHED, JobStatus.FAILED, JobStatus.STOPPED)
 
 
 class JobFailed(RuntimeError):
@@ -379,7 +379,7 @@ def wait_for_job_result(run_id: str, job_id: str, timeout: float | None = None)
             )
         ray_job_id = lifecycle.get_ray_job_id()
         status = get_ray_job_status(ray_job_id)
-        if status in _TERMINAL_JOB_STATES:
+        if status in TERMINAL_JOB_STATES:
             try:
                 result = JobResult.load_from_mlflow(run_id, job_id)
             except FileNotFoundError:
@@ -413,7 +413,7 @@ class JobFuture:
 
     def done(self) -> bool:
         """True once Ray reports the job finished, failed or stopped."""
-        return self.status() in _TERMINAL_JOB_STATES
+        return self.status() in TERMINAL_JOB_STATES
 
     def result(self, timeout: float | None = None) -> Any:
         """Block until the job finishes and return its function's value.

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/cortexgrid/model_serving/lifecycle.py

@@ -220,6 +220,7 @@ def deploy_model(
     wait: bool = False,
     timeout: float | None = 300.0,
     config: DeploymentConfig | None = None,
+    experiment_name: str = "",
 ) -> Deployment:
     """Schedule a Ray Serve app for a previously-saved model and return a
     handle carrying its base URL. The caller (e.g. model-gateway) builds
@@ -298,6 +299,7 @@ def deploy_model(
             "spec": spec,
             "tiers": tiers,
             "url": url,
+            "experiment_name": experiment_name,
             **observation,
         },
     )
@@ -314,6 +316,7 @@ def deploy_model(
         phase=observation["phase"],
         bundle_fingerprint=meta.fingerprint,
         replaced_bundle_fingerprint=observation["replaced_bundle_fingerprint"],
+        experiment_name=experiment_name,
     )
 
 
@@ -327,6 +330,7 @@ def redeploy_model(key: DeploymentKey) -> Deployment:
         key.run_name,
         num_replicas=replica_count_in_spec(record["spec"]),
         config=record["config"],
+        experiment_name=record["experiment_name"],
     )
 
 

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/cortexgrid/model_serving/status.py

@@ -56,6 +56,7 @@ class Deployment:
     phase: str
     bundle_fingerprint: str
     replaced_bundle_fingerprint: str
+    experiment_name: str
 
 
 def replaced_bundle_fingerprint_until_rolled_out(
@@ -82,6 +83,7 @@ def deployment_of_record(record: DeploymentRecord) -> Deployment:
         phase=record["phase"],
         bundle_fingerprint=bundle_fingerprint_in_spec(record["spec"]),
         replaced_bundle_fingerprint=record["replaced_bundle_fingerprint"],
+        experiment_name=record["experiment_name"],
     )
 
 

{cortexgrid-0.3.12 → cortexgrid-0.3.14}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cortexgrid"
-version = "0.3.12"
+version = "0.3.14"
 description = "Connect your ML code to the RoboLab compute cluster — Ray, MLflow, and S3"
 readme = "docs/cortexgrid/README.md"
 license = "Apache-2.0"