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.

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

[REST API] Support more parameters #22

Open
KepingYan opened this issue Jan 3, 2024 · 2 comments
Open

[REST API] Support more parameters #22

KepingYan opened this issue Jan 3, 2024 · 2 comments

Comments

@KepingYan
Copy link
Contributor

Support more request parameters includes suffix, n>1, stop, logprobs, logit_bias, echo, presence_penalty, frequency_penalty. Now only support parameters which included in transformers.generate.
@KepingYan
Copy link
Contributor Author

vllm supports presence, frequency and repetition parameters: vllm/model_executor/layers/sampler.py

carsonwang pushed a commit to carsonwang/llm-on-ray that referenced this issue Jan 9, 2024
@KepingYan
Display information of Ray cluster on UI (intel#22)
7aaaacc 
* Display information of Ray cluster on UI

* UI update: cpu & memory & style

* UI Tab & footer

* fix batch_size & floating dialog

* UI: add fault tolerance

* add note
@xwu99
Copy link
Contributor

xwu99 commented Jan 11, 2024

vLLM engine args: https://docs.vllm.ai/en/latest/models/engine_args.html

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@xwu99 @KepingYan