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.

Sign up for GitHub

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

Jump to bottom

Will you support variable lengths attn kernels? #80

Open

jzhang38 opened this issue Jan 10, 2025 · 0 comments

jzhang38 commented Jan 10, 2025 •

edited

Loading

Dear authors,

Thanks for such a wonderful repo. I notice that the current attn implementation assumes seq_len % 192 == 0, or you will pad them.

ThunderKittens/demos/llama_demo/src/model/transformers_modeling_llama.py

Line 764 in 0cd5947

if q_len % 192 != 0:

Would you add features to support sequences with variable lengths?

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