+
Skip to content

Conversation

guilt
Copy link

@guilt guilt commented Jun 22, 2025

This PR allows us to schedule mochi generation on individual devices, when the user wants to pass a GPU piecemeal to the model. This helps the user optimize heterogenous usage when scheduling GPU jobs across different users.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载