[Spec] Fold the DFLASH worker base into DFlashWorkerV2 on BaseSpecWorker (#27950)
This commit is contained in:
@@ -1172,9 +1172,9 @@ class Scheduler(
|
||||
self.device_module = torch.get_device_module(self.device)
|
||||
|
||||
# FutureMap is always-on: input_ids relay used in both modes.
|
||||
# Workers not on BaseSpecWorker (e.g. NGRAM / DFLASH) lack the
|
||||
# override; fall back to target-only so the helper still produces a
|
||||
# safe decision (no accidental opt-out for unaudited shapes).
|
||||
# Workers without the spec_v2_attn_backends override fall back to
|
||||
# target-only so the helper still produces a safe decision (no
|
||||
# accidental opt-out for unaudited shapes).
|
||||
if self.draft_worker is not None:
|
||||
attn_backends = getattr(
|
||||
self.draft_worker,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user