change: routing logic change for Hugging Face DLCs#5960
Open
dwarez wants to merge 3 commits into
Open
Conversation
huggingface-pytorch-inference images add: huggingface-vllm, huggingface-sglang, huggingface-vllm-omni families metadata Signed-off-by: DWarez <dario.salvati@huggingface.co>
…elBuilder Add ModelServer.VLLM/SGLANG/VLLM_OMNI and teach ModelBuilder's auto-detection to select the new HuggingFace DLCs: text-generation now defaults to vLLM (replacing archived TGI), multimodal tasks route to vLLM-omni, and SGLang is reachable via explicit model_server. TEI/transformers routing is unchanged. Signed-off-by: DWarez <dario.salvati@huggingface.co>
alvarobartt
reviewed
Jun 18, 2026
alvarobartt
left a comment
alvarobartt
left a comment
There was a problem hiding this comment.
Thank you, only nit is in the model_task check for Text Embeddings Inference which is missing text-ranking task, see https://huggingface.co/models?pipeline_tag=text-ranking&other=text-embeddings-inference&sort=trending
Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Depends on #5957.
ModelBuilder's auto-detection will now select:huggingface-vllmfor text-generationhuggingface-vllm-omnifor multimodal taskshuggingface-sglangis opt-in on user sideteilogic unchanged