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

API: add tokenize and tokenize/count routes #7

Closed

celsowm opened this issue Mar 11, 2025 · 0 comments

celsowm commented Mar 11, 2025 •

edited

Loading

Hi!
I used to be a llama cpp python[server] user but now I am trying to migrate to SGLang !

I know v1/openai standard is very limited so each inference server app is trying to extended the routes to facilitate theirs users life.

So as a new user I would like to ask/suggest two new routes for SGLang server:

tokenize: very simple and direct returning the array of tokens.

tokenize/count: optional but useful, the total of tokens (if not at least a simple len(tokenize return) will be enough in client side.

Thanks in advance
Celso

celsowm closed this as completed

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