Skip to content

Fix memory consumption issue with quantized Gemini Nano2 models on CPU #32149

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

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+5 −2
Open

Fix memory consumption issue with quantized Gemini Nano2 models on CPU #32149

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1cb188a
Prevent i8/fp16 to fp32 constant folding in CPU pipeline for Einsum ops
evkotov Sep 18, 2025
32d0516
remove comments
evkotov Sep 22, 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
7 changes: 5 additions & 2 deletions src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@
#include "transformations/op_conversions/convert_topk11_downgrade.hpp"
#include "transformations/op_conversions/detection_output_downgrade.hpp"
#include "transformations/op_conversions/detection_output_upgrade.hpp"
#include "transformations/op_conversions/einsum_decomposition.hpp"
#include "transformations/op_conversions/eye_decomposition.hpp"
#include "transformations/op_conversions/fake_convert_decomposition.hpp"
#include "transformations/op_conversions/fq_decomposition.hpp"
Expand Down Expand Up @@ -460,6 +461,10 @@ void Transformations::PreLpt(const std::vector<ov::element::Type>& defaultPrecis
const bool useLpt = !defaultPrecisions.empty();
CPU_REGISTER_PASS_COMMON(decompression_handling_manager, ov::pass::CompressedGatherTransformation);
CPU_REGISTER_PASS_COMMON(decompression_handling_manager, ov::pass::MarkShapeOfSubgraphs);

// Decompose Einsum before marking dequantization to ensure the pattern can be recognized
CPU_REGISTER_PASS_COMMON(decompression_handling_manager, ov::pass::EinsumDecomposition);

// We need to fuse Transpose to MatMul to have a simpler callback for the next transformation
CPU_REGISTER_PASS_X64(decompression_handling_manager, ov::pass::TransposeMatMul);
CPU_REGISTER_PASS_ARM(decompression_handling_manager, ov::pass::TransposeMatMul);
Expand Down Expand Up @@ -826,8 +831,6 @@ void Transformations::PreLpt(const std::vector<ov::element::Type>& defaultPrecis

// List of enabled/disabled transformations

// Allow FP16 Converts to be folded and FP16 constants to be upgraded to FP32 data type
CPU_DISABLE_PASS_COMMON(manager, ov::pass::DisableDecompressionConvertConstantFolding);
CPU_DISABLE_PASS_COMMON(manager, ov::pass::ConvertCompressedOnlyToLegacy);
CPU_DISABLE_PASS_COMMON(manager, ov::pass::EyeDecomposition);
CPU_DISABLE_PASS_COMMON(manager, ov::pass::ConvertGELU);
Expand Down
Loading