Skip to content
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

NPUW Hotfixes: Memory and L0 pipeline #27828

Merged
merged 5 commits into from
Dec 3, 2024
+7 −8
Merged

NPUW Hotfixes: Memory and L0 pipeline #27828

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3d8b5eb
NPUW: Unfold infer requests (#27319)
dmatveev Nov 21, 2024
76cca6c
[NPUW] LazyTensor refactoring (#27108)
smirnov-alexey Nov 26, 2024
cbb3760
NPUW memory and L0 pipeline hotfixes
smirnov-alexey Nov 29, 2024
49a2cb5
Merge branch 'releases/2024/5' of https://github.com/openvinotoolkit/…
smirnov-alexey Dec 2, 2024
8155c19
Merge branch 'releases/2024/5' into as/release_npuw_mem_hotfix
dmatveev Dec 2, 2024
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: 3 additions & 2 deletions src/plugins/intel_npu/src/plugin/npuw/compiled_model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -723,8 +723,9 @@ std::shared_ptr<ov::ISyncInferRequest> ov::npuw::CompiledModel::create_sync_infe
const auto num_submodels = m_compiled_submodels.size();
for (std::size_t idx = 0u; idx < num_submodels; idx++) {
const auto& comp_model_desc = m_compiled_submodels[idx];
if (!comp_model_desc.replaced_by.has_value()) {
// not a funcall, do nothing
if (!comp_model_desc.replaced_by.has_value() || comp_model_desc.forced_to_fcall) {
// not a funcall, do nothing, or a subgraph that was forced to funcall
// (a 1-call function) - skip
continue;
}
const auto real_idx = comp_model_desc.replaced_by.value();
Expand Down
10 changes: 4 additions & 6 deletions src/plugins/intel_npu/src/plugin/npuw/partitioning/patterns/dcoff.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,12 +96,10 @@ ClosureRemap build_remap(const Function& fbody, const DCOFFParams& params_to) {
LOG_DEBUG("This is an OK parameter, will be kept");
m.closure_remap.push_back(i - fbody._param_offset);

// Check if unpack is indeed required
const auto& type = param->get_element_type();
if (type == ov::element::i4 || type == ov::element::u4 || type == ov::element::i8 ||
type == ov::element::u8) {
m.weights_to_unpack.insert(i - fbody._param_offset);
}
// FIXME: type should be queried from a lazy tensor
// and compared against param->get_element_type()
// to decide 100%
m.weights_to_unpack.insert(i - fbody._param_offset);
}

// Process zero points for parameters
Expand Down
Loading