[Bugfix][MRV2][Spec Decode] Honor dynamic K in autoregressive speculators, 1.2~1.3x kernel perf improvement (#57053)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2026-10-05 14:54:11 -04:00
committed by GitHub
parent c32495d58f
commit 74c5cbcd7b
15 changed files with 190 additions and 18 deletions
@@ -360,6 +360,7 @@ class DFlashSpeculator(DraftModelSpeculator):
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
num_target_tokens = input_batch.num_tokens