Skip to content

fix: Fix _get_accelerator_memory #44

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
svskvar wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: Fix _get_accelerator_memory #44

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f1c697b
fix: Fix _get_accelerator_memory
svskvar Apr 28, 2026
ddffcb8
fix: address _get_accelerator_memory
svskvar Apr 29, 2026
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
23 changes: 14 additions & 9 deletions test/distributed/tensor/debug/test_debug_mode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,10 +52,14 @@
@requires_accelerator

def _get_accelerator_memory():
try:
return torch.accelerator.get_memory_info(0)[1]
except (NotImplementedError):
return 0 # Return 0, as that would help skip the test is not skipped
if not torch.accelerator.is_available():
return -1
device = torch.accelerator.current_accelerator()
if not hasattr(torch, device.type) or not hasattr(
getattr(torch, device.type), "mem_get_info"
):
return -1
return torch.accelerator.get_memory_info(0)[1]

class TestDTensorDebugMode(TestCase):
def tearDown(self):
Expand Down Expand Up @@ -917,12 +921,13 @@ def test_check_hash_mismatches(self):
[call["call"] for call in mismatches], ["aten::sin", "aten::sum"]
)

@unittest.skipIf(
not torch.accelerator.is_available()
or _get_accelerator_memory() < 2**26,
"Being conservative, test peak memory is 25MB?",
)
def test_tensor_hash_redistribute(self):

mem = _get_accelerator_memory()
if mem ==-1:
self.skipTest("No accelerator available or memory query not supported")
if mem < 2**26:
self.skipTest("Requires accelerator with at least 64MB memory")
# test that hashing collectives gives correct results
mesh = DeviceMesh(self.device_type, list(range(self.world_size)))

Expand Down
Loading