Vllm Plugins Python Packages

vllm-mblt

An out-of-tree vLLM plugin for Mobilint NPU runtime integration.

vllm-factory

Production inference for encoder models - ColBERT, GLiNER, ColPali, embeddings etc. - as vLLM plugins for online and in-process deployment

flash-head

FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference

incontext

Exact dynamic output budgeting for Hermes Agent