Metadata-Version: 2.1
Name: ultravox-vllm
Version: 0.5.4.1
Summary: 
Author: Peter Salas
Author-email: peter@fixie.ai
Requires-Python: >=3.10,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Dist: librosa (>=0.10.2.post1,<0.11.0)
Requires-Dist: torchaudio (>=2.4.0,<3.0.0)
Requires-Dist: vllm (==0.5.4)
Requires-Dist: wrapt (>=1.16.0,<2.0.0)
Description-Content-Type: text/markdown

# Ultravox VLLM

This contains a VLLM implementation of Ultravox and some monkeypatches to VLLM's multimodal support to allow audio to be smuggled in via `image_url`s in the OpenAI-compatible server.
