feat: add TASK environment variable for embedding models#255
Open
dvf wants to merge 1 commit intorunpod-workers:mainfrom
Open
feat: add TASK environment variable for embedding models#255dvf wants to merge 1 commit intorunpod-workers:mainfrom
dvf wants to merge 1 commit intorunpod-workers:mainfrom
Conversation
Exposes vllm's --task argument as a TASK env var so users can run embedding models (e.g. BAAI/bge-multilingual-gemma2, Qwen3-VL) that require --task embed. Closes runpod-workers#170
dvf
force-pushed
the
feat/add-task-env-var
branch
from
8468500 to
09443ca
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
TASKenvironment variable (default:auto) that exposes vllm's--taskCLI argumentBAAI/bge-multilingual-gemma2, Qwen3-VL) that require--task embeddocs/configuration.mdCloses #170
Test plan
TASK=embedand verify an embedding model loads correctly with--task embedauto) behavior is unchanged for generation models