[Bugfix][GDN] Reset speculative decode count for an empty draft schedule (#53077)

Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
This commit is contained in:
Kevin H. Luu
2026-08-20 10:33:41 +00:00
committed by GitHub
parent f0c14b4f77
commit 6df7adc17f
+1
View File
@@ -239,6 +239,7 @@ class GDNAttentionMetadataBuilder(AttentionMetadataBuilder[GDNAttentionMetadata]
or num_decode_draft_tokens_cpu[spec_sequence_masks_cpu].sum().item()
== 0
):
num_spec_decodes = 0
spec_sequence_masks = None
spec_sequence_masks_cpu = None
else: