Skip to content

5090推理耗时很久 #36

Open
Open
5090推理耗时很久#36
@geekgogo

Description

@geekgogo
geekgogo
opened on Oct 15, 2025

在5090上使用最新的流式生成的代码，不管是对话还是独白，首包在1s左右，总耗时要十多秒，150字左右的独白甚至耗时38s，这是正常的吗？请问有什么优化的办法？

Metadata

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

    Issue actions