Implement served_model_name to customize model id when use local mode… #749
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
Ying1123
requested changes
Jul 27, 2024
python/sglang/srt/server_args.py
Outdated
| if not self.served_model_name: | ||
| self.served_model_name = self.model_path | ||
| elif isinstance(self.served_model_name, list): | ||
| self.served_model_name = self.served_model_name[0] |
There was a problem hiding this comment.
If served_model_name is given in a wrong format (not a list), self.served_model_name will be None. This could trigger errors in other parts of the changes. Could you check?
There was a problem hiding this comment.
Sure, I'll check it.
merrymercy
requested changes
Jul 27, 2024
python/sglang/srt/server_args.py
Outdated
| @@ -18,6 +18,7 @@ class ServerArgs: | |||
| context_length: Optional[int] = None | |||
| quantization: Optional[str] = None | |||
| chat_template: Optional[str] = None | |||
| served_model_name: Optional[Union[str, List[str]]] = None | |||
There was a problem hiding this comment.
- Why do you allow it to be a list?
- Could you update it to the CLI args as well? https://github.com/sgl-project/sglang/blob/d360a4ea77f0af1f54e94575173f4fa964dc38fc/python/sglang/srt/server_args.py#L98
Ying1123
force-pushed
the
served_model_name
branch
from
d360a4e to
64f300c
Compare
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Outdated suggestions cannot be applied.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.
Motivation
Like vllm, user can load local model with model's id same as huggingface like: mistralai/Mistral-Large-Instruct-2407
Modification
Add an optional arg: served_model_name, change API: /v1/models
Checklist
pre-commit run --all-filesor other linting tools are used to fix potential lint issues.