Skip to content

[BugFix] Enhance test_pos_encoding to support execution on multi-devices #13187

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

Merged
merged 1 commit into from
Feb 16, 2025
+3 −3
Merged

[BugFix] Enhance test_pos_encoding to support execution on multi-devices #13187

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: 3 additions & 3 deletions tests/kernels/test_pos_encoding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ def test_rotary_embedding(
if rotary_dim is None:
rotary_dim = head_size
rope = get_rope(head_size, rotary_dim, max_position, base, is_neox_style)
rope = rope.to(dtype=dtype)
rope = rope.to(dtype=dtype, device=torch.get_default_device())

positions = torch.randint(0, max_position, (batch_size, seq_len))
query_shape = tensor_shape_fn(batch_size, seq_len, num_heads, head_size)
Expand Down Expand Up @@ -125,7 +125,7 @@ def test_batched_rotary_embedding(
"rope_type": "linear",
"factor": (1, )
})
rope = rope.to(dtype=dtype)
rope = rope.to(dtype=dtype, device=torch.get_default_device())

positions = torch.randint(0, max_position, (batch_size, seq_len))
query_shape = tensor_shape_fn(batch_size, seq_len, num_heads, head_size)
Expand Down Expand Up @@ -184,7 +184,7 @@ def test_batched_rotary_embedding_multi_lora(
"rope_type": "linear",
"factor": tuple(scaling_factors)
})
rope = rope.to(dtype=dtype)
rope = rope.to(dtype=dtype, device=torch.get_default_device())

positions = torch.randint(0, max_position, (batch_size, seq_len))
query = torch.randn(batch_size,
Expand Down