Skip to content

budget forcing #117

@Kenwwww

Description

@Kenwwww

anyone knows how to limit thinking length in vllm openai server? it seems like need to adit the logits processor.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions