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.
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
[CPU] Transpose constant folding on cpu plug-in side for MatMul node only #18877
[CPU] Transpose constant folding on cpu plug-in side for MatMul node only #18877
Conversation
2afbd44
to
095ab95
Compare
@dmitry-gorokhov could you start review please? |
src/plugins/intel_cpu/tests/functional/subgraph_tests/src/matmul_decompress_convert.cpp
Outdated
Show resolved
Hide resolved
3038678
to
5c2d62c
Compare
Approved as current soltuion. However we will need to follow-up with more scalable approach: |
35110db
to
42eeae6
Compare
This PR moves constant folding of Transpose nodes (only on weights path of FullyConnected node) to the CPU plugin side, that allows to reduce memory consumption of compile model stage