Skip to content

Fix Issue 57: Add support for L4 GPUs in Vertex jobs #62

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
tripathiji1312 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix Issue 57: Add support for L4 GPUs in Vertex jobs #62

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
6 changes: 5 additions & 1 deletion xmanager/cloud/vertex.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,7 +298,11 @@ def get_machine_spec(job: xm.Job) -> Dict[str, Any]:
for resource, value in requirements.task_requirements.items():
accelerator_type = None
if resource in xm.GpuType:
accelerator_type = 'NVIDIA_TESLA_' + str(resource).upper()
# TODO(b/289373107): Remove this special case.
if resource == xm.GpuType.L4_24TH:
accelerator_type = 'NVIDIA_L4'
else:
accelerator_type = 'NVIDIA_TESLA_' + str(resource).upper()
elif resource in xm.TpuType:
accelerator_type = _CLOUD_TPU_ACCELERATOR_TYPES[resource]
if accelerator_type:
Expand Down
18 changes: 18 additions & 0 deletions xmanager/cloud/vertex_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -155,6 +155,24 @@ def test_get_machine_spec_a100(self):
},
)

def test_get_machine_spec_l4(self):
job = xm.Job(
executable=local_executables.GoogleContainerRegistryImage('name', ''),
executor=local_executors.Vertex(
requirements=xm.JobRequirements(l4_24th=2)
),
args={},
)
machine_spec = vertex.get_machine_spec(job)
self.assertDictEqual(
machine_spec,
{
'machine_type': 'g2-standard-4',
'accelerator_type': vertex.aip_v1.AcceleratorType.NVIDIA_L4,
'accelerator_count': 2,
},
)

def test_get_machine_spec_tpu(self):
job = xm.Job(
executable=local_executables.GoogleContainerRegistryImage('name', ''),
Expand Down