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

[Feature]: Support outlines versions > v0.1.0 #10489

Closed
1 task done
Treparme opened this issue Nov 20, 2024 · 0 comments · Fixed by #10576 · May be fixed by #10490
Closed
1 task done

[Feature]: Support outlines versions > v0.1.0 #10489

Treparme opened this issue Nov 20, 2024 · 0 comments · Fixed by #10576 · May be fixed by #10490

Comments

@Treparme
Copy link

🚀 The feature, motivation and pitch

Outlines (used for guided decoding) has had a minor upgrade on 7th of Oct (ref below).
This has improved their internal workings and should have a good impact on the performance downstream (on vllm).

At the moment the version used by vllm is pinned but we have successfully spinned up vllm ourselves internally with just upgrading this dependency (there are no relevant breaking changes for vllm) and it works out of the box.

https://github.com/dottxt-ai/outlines/releases/tag/0.1.0

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
torymur pushed a commit to dottxt-ai/outlines-core that referenced this issue Dec 2, 2024
I understand that `pickleable` is not your priority right now. But the
`RegexGuide` needs to be pickled for `vllm` production use, which is
multiprocessing-based.

This PR reintroduces this pickling capability + some tests.

I understand that this introduces more effort on your side.

References:
dottxt-ai/outlines#1274
vllm-project/vllm#10490
vllm-project/vllm#10576
vllm-project/vllm#10489

It would also tackle the current caching issues: 
huggingface/text-generation-inference#2766
dottxt-ai/outlines#1283

Closes:
#95
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
1 participant