Add GMI Cloud as an inference provider - #2297
Open
Alas129 wants to merge 2 commits into
Open
Conversation
…ible). Routes chat completions to https://api.gmi-serving.com, with the gmicloud slug mapped to the gmicloudinc Hub org. Follows the existing provider pattern.
Alas129
requested review from
SBrandeis,
hanouticelina and
julien-c
as code owners
July 15, 2026 21:36
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Routes chat completions to https://api.gmi-serving.com, with the gmicloud slug mapped to the gmicloudinc Hub org. Follows the existing provider pattern.
Note
Low Risk
Additive provider wiring using the existing BaseConversationalTask pattern; no changes to auth, routing for other providers, or core client behavior.
Overview
Adds GMI Cloud as a third-party inference provider so
InferenceClientcan targetprovider: "gmicloud"for chat completion (streaming and non-streaming).Requests go to
https://api.gmi-serving.comvia a thinGMICloudConversationalTaskonBaseConversationalTask. The provider is registered inINFERENCE_PROVIDERS,PROVIDERS_HUB_ORGS(gmicloud→gmicloudinc),getProviderHelper, and dev model-mapping stubs. README lists GMI Cloud and links to the partners model API.Integration tests cover
chatCompletionandchatCompletionStreamwithHF_GMICLOUD_KEYand a hardcodeddeepseek-ai/DeepSeek-V4-Promapping.Reviewed by Cursor Bugbot for commit 2cd7845. Bugbot is set up for automated code reviews on this repo. Configure here.