Skip to content

[Question]: RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cuda:1) #25

Closed

Description

@LiweiPE

Describe the issue

The bug is produced when running in multi gpus, since I only can test benchmark_e2e.py with --context_window 512000. Then, I used dual card for Qwen2-7B for context 1M and this error is produced. How to fix?
image

Activity

  1. iofu728 commented on Jul 12, 2024

    @iofu728
    Contributor

    Fixed in #30, please try to use pip install minference -U.

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

Metadata

Metadata

Labels

questionFurther information is requested

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions