Ruonan Wang 0819fad34e support Llama2-7B / Llama3-8B for NPU C++ (#12431) ... * support llama2 * update * support fused_layers=4 for Llama2-7B		2024-11-22 18:47:19 +08:00
..
llm	support Llama2-7B / Llama3-8B for NPU C++ (#12431)	2024-11-22 18:47:19 +08:00