Wang, Jian4 209c3501e6 LLM: Optimize qwen1.5 moe model (#10706) ... * update moe block * fix style * enable optmize MLP * enabel kv_cache * enable fuse rope * enable fused qkv * enable flash_attention * error sdp quantize * use old api * use fuse * use xetla * fix python style * update moe_blocks num * fix output error * add cpu sdpa * update * update * update		2024-04-18 14:54:05 +08:00
..
llm	LLM: Optimize qwen1.5 moe model (#10706)	2024-04-18 14:54:05 +08:00