Skip to content

NPUW: LLMInferRequest - not copy kvcache for last generated token#28489

Merged
TolyaTalamanov merged 1 commit intoopenvinotoolkit:masterfrom TolyaTalamanov:at/npuw-llm-pipeline-stop-when-kvcache-is-fullJan 16, 2025
+4

Commits

Commits on Jan 16, 2025