Skip to content

Address a DML regression caused by the continuous decoding changes #1159

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

Jump to bottom
Merged
merged 8 commits into from
Jan 13, 2025
Merged

Address a DML regression caused by the continuous decoding changes #1159

merged 8 commits into from
Jan 13, 2025

Conversation

@baijumeswani
Copy link
Collaborator

@baijumeswani baijumeswani commented Dec 19, 2024 •
edited
Loading

Issues that this PR resolves:

  • For DML EP, the input ids must be allocated on CPU for the prompt case.
  • logits must use the static buffer only after the first Update for DML.
  • DML memory device type was unhandled due to changes in ORT

aciddelgado
aciddelgado reviewed Jan 10, 2025
View reviewed changes
@baijumeswani baijumeswani merged commit 49eb184 into main Jan 13, 2025
14 checks passed
@baijumeswani baijumeswani deleted the baijumeswani/fix-dml branch January 13, 2025 18:18
baijumeswani added a commit that referenced this pull request Jan 13, 2025
@baijumeswani
Address a DML regression caused by the continuous decoding changes (#…
684c7f2 
…1159)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@aciddelgado aciddelgado aciddelgado approved these changes

@RyanUnderhill RyanUnderhill Awaiting requested review from RyanUnderhill

Assignees

No one assigned

Labels

rel-0.6.0

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@baijumeswani @aciddelgado