Add router name to /info endpoint #1854
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Nilabhra
pushed a commit
to TII-AI-Research-Center/text-generation-inference
that referenced
this pull request
May 14, 2024
Add `router` key in `/info` endpoint and set it to
`env!("CARGO_PKG_NAME")` => so always set to `"text-generation-router"`
in TGI. Happy to change the naming if you think of a better one
(framework? package_name?)
The goal is to use this information in `InferenceClient` to know the
model is served with TGI. At the moment we can use
https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2/info
to infer it is TGI-served because it returns information but having a
proper key would be better.
For context, a transformers-served model is only outputting `{"ok":
"ok"}` (see
[here](https://api-inference.huggingface.co/models/microsoft/DialoGPT-large/info)).
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add
routerkey in/infoendpoint and set it toenv!("CARGO_PKG_NAME")=> so always set to"text-generation-router"in TGI. Happy to change the naming if you think of a better one (framework? package_name?)The goal is to use this information in
InferenceClientto know the model is served with TGI. At the moment we can use https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2/info to infer it is TGI-served because it returns information but having a proper key would be better.For context, a transformers-served model is only outputting
{"ok": "ok"}(see here).