[Bugfix][Spec Decode] Keep heterogeneous-vocab draft models on Model Runner V1 (#59541)

Signed-off-by: Nishant Revur <kumrfni@amazon.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Nishant Revur
2026-10-06 18:03:44 +00:00
committed by GitHub
co-authored by Claude
parent 3403e0f176
commit ad0f67a7ec
2 changed files with 29 additions and 0 deletions
+5
View File
@@ -3159,6 +3159,11 @@ class VllmConfig:
):
unsupported.append("parallel drafting for EAGLE speculative decoding")
# The V2 draft-model speculator has no token mapping between the
# draft and target vocabularies (TLI is TBD in #47172).
if getattr(speculative_config, "use_heterogeneous_vocab", False):
unsupported.append("heterogeneous-vocabulary draft models")
if self.parallel_config.use_ubatching:
unsupported.extend(self._get_dbo_unsupported_features())