快速登录
Your performance data looks okay.NUMA can indeed help with performance, but only to a limited extent, and yes for now it requires memory that is at least double the size of the model.文档中描述amx会对BF16 gguf的参数进行在线量化,那么如果我启用amx,在双插槽的情况下是需要至少2.6T还是之前q4版本双插槽两倍的内存也就2TB就足够了呢
Your performance data looks okay.
NUMA can indeed help with performance, but only to a limited extent, and yes for now it requires memory that is at least double the size of the model.
文档中描述amx会对BF16 gguf的参数进行在线量化,那么如果我启用amx,在双插槽的情况下是需要至少2.6T还是之前q4版本双插槽两倍的内存也就2TB就足够了呢
点开一个聊天,右上角点开三点,向下滑有消息免打扰,把这个关掉,就能接受到消息提示音,静音标志就能撤销了 。
单人聊天或者群聊都可以的
社交账号登录