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

Remove repeated concat of prompt and decode tokens in detokenization #139

Open
masahi opened this issue Jan 3, 2024 · 0 comments
Open
Labels
bug Something isn't working

Comments

@masahi
Copy link
Member

masahi commented Jan 3, 2024

As of the parallel sampling work, we are maintaining prompt and decode tokens separately. However, to preserve the output of detokenization, I had to concat them repeatedly:
https://github.com/octoml/mlc-llm/blob/batch-serving/serve/mlc_serve/engine/engine_common.py#L97-L99

It seems very wasteful to do concat and detokenization of the entire tokens repeatedly while what we really need is only the new delta at the postfix.

@masahi masahi added the bug Something isn't working label Jan 3, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant