[Perf] Pin CPU tensors before non_blocking H2D in three MM paths (#54292)
Signed-off-by: Keyi Li <likey6688@gmail.com> Co-authored-by: Keyi Li <likey6688@gmail.com> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Keyi Li
Claude Opus 4.7
parent
93ab92be0c
commit
46a83642f6
@@ -259,10 +259,7 @@ class MMEncoderAttention(CustomOp):
|
||||
sequence_lengths = add_padding_to_seqlens(
|
||||
sequence_lengths, len(sequence_lengths), 0
|
||||
)
|
||||
sequence_lengths = torch.from_numpy(sequence_lengths).to(
|
||||
device, non_blocking=True
|
||||
)
|
||||
return sequence_lengths
|
||||
return async_tensor_h2d(sequence_lengths, device=device)
|
||||
|
||||
@classmethod
|
||||
def maybe_recompute_cu_seqlens(
|
||||
|
||||
Reference in New Issue
Block a user