openvino
9813b4e5 - NPUW: Three-model pipeline (#31460)

Commit
275 days ago
NPUW: Three-model pipeline (#31460) ### Details: - *Separated Vocab MatMul into additional model* - *Called infer for additional model in LLMInferRequest* ### Dependencies: - *OpenVINO GenAI PR* : https://github.com/openvinotoolkit/openvino.genai/pull/2317 ### Tickets: - *EISW-165218* ### Note: - *Regression was found with the PR in the previous merge, PR was reverted, this regression got fixed in current PR* --------- Co-authored-by: Dmitry Matveev <dmitry.matveev@intel.com>
Author
Parents
Loading