{"library":"vllm-omni","type":"library","category":null,"description":"vLLM-Omni is a framework for efficient model inference with omni-modality models, built on top of vLLM. It supports speech, image, video, audio, and multimodal generation, aligned with upstream vLLM releases. Current version is 0.20.0, with active development and monthly release cadence.","language":"python","status":"active","version":"0.20.0","tags":["vllm","multimodal","inference","omni","speech","image","video","audio"],"last_verified":"Sat May 09","install":[{"cmd":"pip install vllm-omni","imports":["from vllm import LLM","from vllm import SamplingParams","from vllm.engine.async_llm_engine import AsyncLLMEngine"]}],"homepage":null,"github":"https://github.com/vllm-project/vllm-omni","docs":"https://vllm-omni.readthedocs.io","changelog":null,"pypi":"https://pypi.org/project/vllm-omni/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}