Skip to content

[None][fix] AutoDeploy: set enable_spec_decode on ADEngine for disagg #15260

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
govind-ramnarayan merged 3 commits into from
Jun 12, 2026
Merged

[None][fix] AutoDeploy: set enable_spec_decode on ADEngine for disagg #15260

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
73ed620
[None][fix] AutoDeploy: set enable_spec_decode on ADEngine for disagg
Shixiaowei02 Jun 11, 2026
95b10a6
Merge branch 'main' into fix/ad-disagg-enable-spec-decode
govind-ramnarayan Jun 11, 2026
68d8f45
Merge branch 'main' into fix/ad-disagg-enable-spec-decode
govind-ramnarayan Jun 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions tensorrt_llm/_torch/auto_deploy/shim/ad_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -494,6 +494,11 @@ def __init__(
else:
self.max_total_draft_tokens = 0

# ADEngine skips PyTorchModelEngine.__init__, so set the spec-decode
# flags that shared PyExecutor code expects on a ModelEngine.
self.is_spec_decode = self.spec_config is not None
self.enable_spec_decode = self.is_spec_decode

# For compatibility with PyTorchModelEngine utilities
self.batch_size = cache_seq_interface.info.max_batch_size

Expand Down
Loading