Skip to content

[QNN-EP] Disable file mapping for embedded cache #27627

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
yuslepukhin merged 4 commits into from
Mar 18, 2026
Merged

[QNN-EP] Disable file mapping for embedded cache #27627

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4b1ee33
[QNN-EP] Disable file mapping for embedded cache
Mar 12, 2026
361c087
Resolve typo
Mar 12, 2026
38b51a4
Resolve execution bug
Mar 12, 2026
f21a93c
Move logic into macro
Mar 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
3 changes: 2 additions & 1 deletion onnxruntime/core/providers/qnn/builder/qnn_backend_manager.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1367,7 +1367,8 @@ Status QnnBackendManager::LoadCachedQnnContextFromBuffer(char* buffer, uint64_t

void* bin_buffer = nullptr;
#ifdef QNN_FILE_MAPPED_WEIGHTS_AVAILABLE
if (file_mapped_weights_enabled_) {
// A nonzero buffer length implies an embedded context
if (file_mapped_weights_enabled_ && buffer_length == 0) {
ORT_RETURN_IF(!file_mapper_, "Attemping to use File Mapping feature but file_mapper_ is uninitialized");

ORT_RETURN_IF_ERROR(GetFileSizeIfValid(context_bin_filepath, buffer_length));
Expand Down
5 changes: 5 additions & 0 deletions onnxruntime/core/providers/qnn/qnn_execution_provider.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -488,6 +488,11 @@ QNNExecutionProvider::QNNExecutionProvider(const ProviderOptions& provider_optio
enable_file_mapped_weights_ = false;
LOGS_DEFAULT(WARNING) << "File mapped weights feature is only available on Windows arm64 devices for QNN API versions >= 2.32. "
<< "Feature will be disabled by default";
#else
if (qnn_context_embed_mode_ && enable_file_mapped_weights_) {
enable_file_mapped_weights_ = false;
LOGS_DEFAULT(WARNING) << "File mapped weights feature is incompatible with embedded EP contexts. Feature will be disabled by default.";
}
#endif

static const std::string QNN_DEVICE_ID = "device_id";
Expand Down
Loading