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
感觉现在mix的开发重心是放在复现更多的模型上面吗?现在torch+hf的高歌猛进,基本上多模的代码都是10行代码以内的调用,那mix的核心是什么呢?集成了更多的模型吗?刚在看DiffusionPipeline的实现代码,enable_model_cpu_offload在ppdiffusers没有实现,torch版本中它的核心是from accelerate import cpu_offload_with_hook,那pp没有accelerate库,所以也不能直接导进来;再比如torch版本的sd3,在单卡4090上可以跑完,但是pp版本的则需要30g左右,无法在4090上跑通;当下的路是不是需要思考下怎么走,比如走轻量级多模,广大同胞其实是没有多少算力的,现在如果说跑个sd模型需要个A100才能跑,或许大多数都是跑不动的,如果说能在3060/4070这种消费端卡上,跑上一些有意义的模型,比如每个类(问答类/图像生成类/视频生成类这些)都做一两个普惠型的模型,可能会让更多人了解到mix团队的努力?
The text was updated successfully, but these errors were encountered:
lyuwenyu
No branches or pull requests
感觉现在mix的开发重心是放在复现更多的模型上面吗?现在torch+hf的高歌猛进,基本上多模的代码都是10行代码以内的调用,那mix的核心是什么呢?集成了更多的模型吗?刚在看DiffusionPipeline的实现代码,enable_model_cpu_offload在ppdiffusers没有实现,torch版本中它的核心是from accelerate import cpu_offload_with_hook,那pp没有accelerate库,所以也不能直接导进来;再比如torch版本的sd3,在单卡4090上可以跑完,但是pp版本的则需要30g左右,无法在4090上跑通;当下的路是不是需要思考下怎么走,比如走轻量级多模,广大同胞其实是没有多少算力的,现在如果说跑个sd模型需要个A100才能跑,或许大多数都是跑不动的,如果说能在3060/4070这种消费端卡上,跑上一些有意义的模型,比如每个类(问答类/图像生成类/视频生成类这些)都做一两个普惠型的模型,可能会让更多人了解到mix团队的努力?
The text was updated successfully, but these errors were encountered: