Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

QwenVL2.5 bfloat16 Type Issue #706

Open
qirui-chen opened this issue Feb 1, 2025 · 0 comments
Open

QwenVL2.5 bfloat16 Type Issue #706

qirui-chen opened this issue Feb 1, 2025 · 0 comments

Comments

@qirui-chen
Copy link

qirui-chen commented Feb 1, 2025

In the code, the tensor is forcibly cast to float32, while cos and sin may be inconsistent with the tensor due to the model type being bfloat16.

This problem occurred when using the flash attention 2 & bf16 Qwen2.5VL model.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant