Yuwen Hu a0150bb205 [LLM] Move embedding layer to CPU for iGPU inference (#9343) ... * Move embedding layer to CPU for iGPU llm inference * Empty cache after to cpu * Remove empty cache as it seems to have some negative effect to first token		2023-11-03 11:13:45 +08:00
..
llm	[LLM] Move embedding layer to CPU for iGPU inference (#9343)	2023-11-03 11:13:45 +08:00