Add LeptonExecutor support

docs/source/guides/execution.md

@@ -7,6 +7,7 @@ Each execution of a single configured task requires an executor. Nemo-Run provid
 - `run.DockerExecutor`
 - `run.SlurmExecutor` with an optional `SSHTunnel` for executing on Slurm clusters from your local machine
 - `run.SkypilotExecutor` (available under the optional feature `skypilot` in the python package).
+- `run.LeptonExecutor`
 
 A tuple of task and executor form an execution unit. A key goal of NeMo-Run is to allow you to mix and match tasks and executors to arbitrarily define execution units.
 
@@ -41,6 +42,7 @@ The packager support matrix is described below:
 | SlurmExecutor | run.Packager, run.GitArchivePackager, run.PatternPackager, run.HybridPackager |
 | SkypilotExecutor | run.Packager, run.GitArchivePackager, run.PatternPackager, run.HybridPackager |
 | DGXCloudExecutor | run.Packager, run.GitArchivePackager, run.PatternPackager, run.HybridPackager |
+| LeptonExecutor   | run.Packager, run.GitArchivePackager, run.PatternPackager, run.HybridPackager |
 
 `run.Packager` is a passthrough base packager.
 
@@ -264,3 +266,40 @@ def your_dgx_executor(nodes: int, gpus_per_node: int, container_image: str):
 ```
 
 For a complete end-to-end example using DGX Cloud with NeMo, refer to the [NVIDIA DGX Cloud NeMo End-to-End Workflow Example](https://docs.nvidia.com/dgx-cloud/run-ai/latest/nemo-e2e-example.html).
+
+#### LeptonExecutor
+
+The `LeptonExecutor` integrates with an NVIDIA DGX Cloud Lepton cluster's Python SDK to launch distributed jobs. It uses API calls behind the Lepton SDK to authenticate, identify the target node group and resource shapes, and submit the job specification which will be launched as a batch job on the cluster.
+
+Here's an example configuration:
+
+```python
+def your_lepton_executor(nodes: int, gpus_per_node: int, container_image: str):
+    # Ensure these are set correctly for your DGX Cloud environment
+    # You might fetch these from environment variables or a config file
+    resource_shape = "gpu.8xh100-80gb" # Replace with your desired resource shape representing the number of GPUs in a pod
+    node_group = "my-node-group"  # The node group to run the job in
+    nemo_run_dir = "/nemo-workspace/nemo-run"  # The NeMo-Run directory where experiments are saved
+    # Define the remote storage directory that will be mounted in the job pods
+    # Ensure the path specified here contains your NEMORUN_HOME
+    storage_path = "/nemo-workspace" # The remote storage directory to mount in jobs
+    mount_path = "/nemo-workspace" # The path where the remote storage directory will be mounted inside the container
+
+    executor = run.LeptonExecutor(
+        resource_shape=resource_shape,
+        node_group=node_group,
+        container_image=container_image,
+        nodes=nodes,
+        nemo_run_dir=nemo_run_dir,
+        gpus_per_node=gpus_per_node,
+        mounts=[{"path": storage_path, "mount_path": mount_path}],
+        # Optional: Add custom environment variables or PyTorch specs if needed
+        env_vars=common_envs(),
+        # packager=run.GitArchivePackager() # Choose appropriate packager
+    )
+    return executor
+
+# Example usage:
+executor = your_lepton_executor(nodes=4, gpus_per_node=8, container_image="your-nemo-image")
+
+```

docs/source/guides/why-use-nemo-run.md

@@ -29,6 +29,7 @@ But once defined, it is seamless to launch your tasks. Currently, we support the
 - LocalExecutor
 - SlurmExecutor
 - SkypilotExecutor
+- LeptonExecutor
 
 This means that you can launch your configured task on one slurm cluster or the other, on a Kubernetes cluster, on one cloud or the other, or on all of them at the same time.
 

docs/source/index.rst

@@ -38,6 +38,12 @@ will install Skypilot w all clouds
 
 You can also manually install Skypilot from https://skypilot.readthedocs.io/en/latest/getting-started/installation.html
 
+If using DGX Cloud Lepton, use the following command to install the Lepton CLI:
+
+``pip install leptonai``
+
+To authenticate with the DGX Cloud Lepton cluster, navigate to the **Settings > Tokens** page in the DGX Cloud Lepton UI and copy the ``lep login`` command shown on the page and run it in the terminal.
+
 Make sure you have `pip` installed and configured properly.
 
 

nemo_run/__init__.py

@@ -19,19 +19,20 @@
 
 from nemo_run import cli
 from nemo_run.api import autoconvert, dryrun_fn
+from nemo_run.cli.lazy import LazyEntrypoint, lazy_imports
 from nemo_run.config import Config, ConfigurableMixin, Partial, Script
 from nemo_run.core.execution.base import Executor, ExecutorMacros, import_executor
 from nemo_run.core.execution.dgxcloud import DGXCloudExecutor
 from nemo_run.core.execution.docker import DockerExecutor
 from nemo_run.core.execution.launcher import FaultTolerance, SlurmRay, SlurmTemplate, Torchrun
+from nemo_run.core.execution.lepton import LeptonExecutor
 from nemo_run.core.execution.local import LocalExecutor
 from nemo_run.core.execution.skypilot import SkypilotExecutor
 from nemo_run.core.execution.slurm import SlurmExecutor
 from nemo_run.core.packaging import GitArchivePackager, HybridPackager, Packager, PatternPackager
 from nemo_run.core.tunnel.client import LocalTunnel, SSHTunnel
 from nemo_run.devspace.base import DevSpace
 from nemo_run.help import help
-from nemo_run.cli.lazy import LazyEntrypoint, lazy_imports
 from nemo_run.package_info import __package_name__, __version__
 from nemo_run.run.api import run
 from nemo_run.run.experiment import Experiment
@@ -58,6 +59,7 @@
     "GitArchivePackager",
     "PatternPackager",
     "help",
+    "LeptonExecutor",
     "LocalExecutor",
     "LocalTunnel",
     "Packager",

nemo_run/core/execution/__init__.py

@@ -13,9 +13,16 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from nemo_run.core.execution.dgxcloud import DGXCloudExecutor
+from nemo_run.core.execution.lepton import LeptonExecutor
 from nemo_run.core.execution.local import LocalExecutor
 from nemo_run.core.execution.skypilot import SkypilotExecutor
 from nemo_run.core.execution.slurm import SlurmExecutor
-from nemo_run.core.execution.dgxcloud import DGXCloudExecutor
 
-__all__ = ["LocalExecutor", "SlurmExecutor", "SkypilotExecutor", "DGXCloudExecutor"]
+__all__ = [
+    "LocalExecutor",
+    "SlurmExecutor",
+    "SkypilotExecutor",
+    "DGXCloudExecutor",
+    "LeptonExecutor",
+]