[Perf] Keep non-speculative GDN decode on the standard path (#59735)
Signed-off-by: DimensionSTP <65501090+DimensionSTP@users.noreply.github.com> Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg> Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg> Co-authored-by: Kimi Code <noreply@moonshot.ai>
This commit is contained in:
co-authored by
Thien Tran
Kimi Code
parent
24df2d3fc7
commit
e4294144a8
@@ -194,7 +194,7 @@ def test_fused_forward_uses_packed_entrypoint() -> None:
|
||||
ba = torch.randn(num_tokens, 2 * HV, dtype=torch.bfloat16, device=device)
|
||||
layer = types.SimpleNamespace(
|
||||
prefix=PREFIX,
|
||||
enable_fused_gdn_decode=True,
|
||||
enable_fused_gdn_spec_decode=True,
|
||||
norm=types.SimpleNamespace(
|
||||
weight=torch.empty(V, dtype=torch.bfloat16, device=device)
|
||||
),
|
||||
|
||||
Reference in New Issue
Block a user