Skip to content

Adding DirectML fallback support in heuristics in EP #84

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

Draft
urpetkov-amd wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Adding DirectML fallback support in heuristics in EP #84

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion src/amdgpu/gpu_ep.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,6 @@ ExecutionProvider::ExecutionProvider(ProviderFactory& factory, std::string_view
}

const ProviderInfo info{provider_options};
backend_ = BackendForProfile(info.profile);

// Telemetry is an internal EP facility. It is enabled by default and uses the
// platform default directory (LocalLow on Windows).
Expand Down Expand Up @@ -296,6 +295,7 @@ ExecutionProvider::ExecutionProvider(ProviderFactory& factory, std::string_view
// Explicit profile is honored; Auto/Optimized derives from (ASIC, model_arch). select_backend()
// (inside route_by_heuristic) applies both, so the result covers every profile value.
const Profile effective = route_by_heuristic();
backend_ = BackendForProfile(effective);

#ifdef USE_DML
if (effective == Profile::Eager) {
Expand Down
Loading