We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
这个慢的原因是vpn连接gpt4o的问题吗? 截图、ocr、gpt做决策 这几个过程,到底是哪块慢呢?
The text was updated successfully, but these errors were encountered:
慢的原因主要有两个:
解决方案可以将部分模块设计为并行,例如planning和上一阶段的reflection是可以并行的,如果反思结果正确,则可以省去一次调用,如果错误,则回退操作并重新执行planning即可,不会产生额外的延时。
同时,ocr和sam也是可以并行的,并且可以放到GPU上加速。不过,想要速度真正达到可用,还需要解决基模型推理的速度,这将是下一步我们v3工作的重点。
Sorry, something went wrong.
好想法,我最近也在做类似的项目。要提升速度瓶颈始终在模型上,如果模型性能够用的话甚至可以省略反思记忆等流程,直接输出action,这样就能大幅提升速度。
是的,我们也提供了反思和记忆的开关,如果任务难度不高,可以尝试关闭。
No branches or pull requests
这个慢的原因是vpn连接gpt4o的问题吗?
截图、ocr、gpt做决策
这几个过程,到底是哪块慢呢?
The text was updated successfully, but these errors were encountered: