Repository navigation
Detect HTTP worker runtime via /v1/models - #4368
Merged
Merged
Conversation
Probe GET /v1/models first and dispatch on the first model's owned_by, the same way SMG detects the runtime. Until the runtime is known, what a gRPC worker, a starting worker, or an unrelated HTTP server produces (request errors, 404, bodies that are not a model list) is logged at debug level. Other status codes, vLLM HTTP workers (not supported, use gRPC), and unknown runtimes are logged as warnings. For SGLang, fall back to the deprecated /get_server_info on 404 (SGLang < 0.5.6), and validate /server_info and gRPC server_args with pydantic models. Once the runtime is detected, every failure is a warning.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Probe GET /v1/models first and dispatch on the first model's owned_by, the same way SMG detects the runtime. Until the runtime is known, what a gRPC worker, a starting worker, or an unrelated HTTP server produces (request errors, 404, bodies that are not a model list) is logged at debug level. Other status codes, vLLM HTTP workers (not supported, use gRPC), and unknown runtimes are logged as warnings.
For SGLang, fall back to the deprecated /get_server_info on 404 (SGLang < 0.5.6), and validate /server_info and gRPC server_args with pydantic models. Once the runtime is detected, every failure is a warning.