GRPO 超长序列 #51

Open

opened

请问一下在给定的示例脚本verl_grpo中，我看response最长已经到了24000，而且batch size为1024，sp=1。在A800环境下不会OOM吗？我在A800环境下，长度在10000左右就会OOM

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Fields

No fields configured for issues without a type.

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests