Skip to content

fix: Add ml.p5e.48xlarge and ml.p5.48xlarge to EFA instance lists #5492

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
srujithpoondla03 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: Add ml.p5e.48xlarge and ml.p5.48xlarge to EFA instance lists #5492

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
3 changes: 3 additions & 0 deletions sagemaker-core/src/sagemaker/core/modules/train/container_drivers/common/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,12 +50,15 @@
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

SM_EFA_RDMA_INSTANCES = [
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

Expand Down
3 changes: 3 additions & 0 deletions ...e/src/sagemaker/core/remote_function/runtime_environment/bootstrap_runtime_environment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,12 +75,15 @@
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

SM_EFA_RDMA_INSTANCES = [
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

Expand Down
3 changes: 3 additions & 0 deletions sagemaker-train/src/sagemaker/train/container_drivers/common/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,12 +50,15 @@
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

SM_EFA_RDMA_INSTANCES = [
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

Expand Down
3 changes: 3 additions & 0 deletions .../src/sagemaker/train/remote_function/runtime_environment/bootstrap_runtime_environment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,12 +75,15 @@
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

SM_EFA_RDMA_INSTANCES = [
"ml.p4d.24xlarge",
"ml.p4de.24xlarge",
"ml.p5.48xlarge",
"ml.p5e.48xlarge",
"ml.trn1.32xlarge",
]

Expand Down
26 changes: 26 additions & 0 deletions sagemaker-train/tests/unit/train/container_drivers/test_torchrun_driver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
import sys
import json

import pytest
from unittest.mock import patch, MagicMock

sys.modules["utils"] = MagicMock()
Expand Down Expand Up @@ -146,3 +147,28 @@ def test_create_commands_multi_node(

command = torchrun_driver.create_commands()
assert command == expected_command


@pytest.mark.parametrize("instance_type", ["ml.p5.48xlarge", "ml.p5e.48xlarge"])
@patch.dict(
os.environ,
{
"SM_NETWORK_INTERFACE_NAME": "eth0",
"SM_HOST_COUNT": "2",
"SM_MASTER_ADDR": "algo-1",
"SM_MASTER_PORT": "7777",
"SM_CURRENT_HOST_RANK": "0",
"SM_HPS": json.dumps({}),
"SM_DISTRIBUTED_CONFIG": json.dumps(DUMMY_DISTRIBUTED),
"SM_ENTRY_SCRIPT": "script.py",
},
)
def test_p5_p5e_efa_environment_setup(instance_type):
"""Test that P5 and P5e instances are in EFA instance lists."""
from sagemaker.train.container_drivers.common.utils import (
SM_EFA_NCCL_INSTANCES,
SM_EFA_RDMA_INSTANCES,
)

assert instance_type in SM_EFA_NCCL_INSTANCES
assert instance_type in SM_EFA_RDMA_INSTANCES