Skip to content
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

TestLowCpuMemUsage UT get device by device_name #6397

Merged
merged 3 commits into from
Aug 29, 2024
Merged

TestLowCpuMemUsage UT get device by device_name #6397

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
33c8ef6
TestLowCpuMemUsage UT get device by device_name
raza-sikander Aug 22, 2024
957d6db
Merge branch 'microsoft:master' into inf
raza-sikander Aug 22, 2024
4c233b0
Merge branch 'master' into inf
loadams Aug 29, 2024
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
10 changes: 8 additions & 2 deletions tests/unit/inference/test_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,6 +298,12 @@ def verify_injection(module):
verify_injection(model)


# Used to Get Device name
def getDeviceId(local_rank):
device = torch.device(f"{get_accelerator().device_name(local_rank)}")
return device


# Verify that test is valid
def validate_test(model_w_task, dtype, enable_cuda_graph, enable_triton):
model, task = model_w_task
Expand Down Expand Up @@ -484,8 +490,8 @@ def test(
pytest.skip(f"Acceleraor {get_accelerator().device_name()} does not support {dtype}.")

local_rank = int(os.getenv("LOCAL_RANK", "0"))

pipe = pipeline(task, model=model, model_kwargs={"low_cpu_mem_usage": True}, device=local_rank, framework="pt")
device = getDeviceId(local_rank)
pipe = pipeline(task, model=model, model_kwargs={"low_cpu_mem_usage": True}, device=device, framework="pt")
bs_output = pipe(query, **inf_kwargs)
pipe.model = deepspeed.init_inference(pipe.model,
mp_size=self.world_size,
Expand Down
Loading