[Bugfix][MRV2][Spec Decode] Accept num_speculative_tokens in NgramGPUSpeculator.propose (#60300)

Signed-off-by: cheesecake <farzanaman99@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Cheese Cake
2026-10-06 15:02:04 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent ae19af883a
commit b6d8e8afd9
@@ -231,6 +231,7 @@ class NgramGPUSpeculator(BaseSpeculator):
skip_attn_for_dummy_run: bool = False,
mm_inputs: tuple[list[torch.Tensor], torch.Tensor] | None = None,
is_profile: bool = False,
num_speculative_tokens: int | None = None,
) -> torch.Tensor:
num_reqs = input_batch.num_reqs
if dummy_run: