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

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

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

Metadata

Assignees

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