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

[LLM] [NPU] StaticLLMPipeline: support weightless caching #1635

Merged
merged 7 commits into from
Feb 17, 2025
+24 −3
Merged

[LLM] [NPU] StaticLLMPipeline: support weightless caching #1635

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
d67bad2
Depending on the cache mode call different compile_model overload
smirnov-alexey Jan 27, 2025
2575a64
Merge branch 'master' of https://github.com/openvinotoolkit/openvino.…
smirnov-alexey Jan 27, 2025
a62b527
Address review comment
smirnov-alexey Jan 31, 2025
aa613b3
Add config to import
smirnov-alexey Jan 31, 2025
a521189
Make weightless a default flow
smirnov-alexey Feb 12, 2025
b65acd0
Merge branch 'master' into as/npuw_weightless
smirnov-alexey Feb 14, 2025
79b8775
Merge branch 'master' into as/npuw_weightless
smirnov-alexey Feb 17, 2025
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
Prev Previous commit
Next Next commit
Loading
Loading status checks…
Address review comment
@smirnov-alexey
smirnov-alexey committed Jan 31, 2025
commit a62b5270baca550d0a2112df2750fbd7b3c9ae0c
4 changes: 2 additions & 2 deletions src/cpp/src/llm_pipeline_static.cpp
View file
Original file line number Diff line number Diff line change
@@ -722,8 +722,8 @@ StatefulLLMPipeline::StatefulLLMPipeline(
ov::AnyMap properties = config;
std::shared_ptr<ov::CompiledModel> compiled;
// CACHE_DIR + weightless flow support
auto cache_mode = get_option<std::string>(config, "CACHE_MODE");
if (cache_mode.has_value() && *cache_mode == "OPTIMIZE_SIZE") {
auto cache_mode = get_option<CacheMode>(config, "CACHE_MODE");
if (cache_mode.has_value() && *cache_mode == CacheMode::OPTIMIZE_SIZE) {
compiled = setupAndCompileModel(models_path / "openvino_model.xml", model_desc, properties);
} else {
auto model = genai::utils::singleton_core().read_model(models_path / "openvino_model.xml", {}, config);