模型响应内容会很卡顿,同样的接口在 Cherry Studio 是正常的 #6686
Unanswered
huangkairan
asked this question in
General Question | 普通问题
Replies: 2 comments 10 replies
-
@sxjeru 我怀疑是 #5824 的问题,我最近也有发现,只要消息数超过10条就输出很卡,看下有没有解法?没有的话准备回滚了 |
Beta Was this translation helpful? Give feedback.
6 replies
-
@huangkairan 请问有开启客户端请求吗,Cherry Studio 那边没事或许是因为它完全是客户端请求。 可以的话请按 F12 打开控制台,点击“网络”页签,然后再次请求,最后把“响应”中的内容粘贴上来。并目视观察响应中流内容更新速度是否符合卡顿情况,也就是卡几秒才刷出下一行。 |
Beta Was this translation helpful? Give feedback.
4 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
效果见录屏:https://drive.google.com/file/d/1qAaQXogAzXbbXyUFntVZdPqlrdXTyqv3/view?usp=drive_link
服务端数据库版本私有化部署,未开启客户端请求
Beta Was this translation helpful? Give feedback.
All reactions