Kai Huang 689889482c Reduce max_cache_pos to reduce Baichuan2-13B memory (#9694) ... * optimize baichuan2 memory * fix * style * fp16 mask * disable fp16 * fix style * empty cache * revert empty cache		2023-12-26 19:51:25 +08:00
..
llm	Reduce max_cache_pos to reduce Baichuan2-13B memory (#9694)	2023-12-26 19:51:25 +08:00