An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
While Large Multimodal Models excel in comprehension, high-throughput inference engines lack native support for multimodal generation. This is severe in Speech Language Models, where generating multi-layered audio tokens via decoupled AR+NAR or synchronous Multi-Token Prediction (MTP) with delay-pattern interleaving conflicts with standard single-stream loops. We present a vLLM-based inference pipeline for unified speech understanding and generation. We extend autoregressive decoding to natively execute delay-pattern de-interleaving and coordinated multi-stream sampling, integrating an on-GPU
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorHaoran Wang →
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
- Linked via arxiv authorJinchuan Tian →
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
- Linked via arxiv authorSiddhant Arora →
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation
- Linked via arxiv authorShinji Watanabe →
An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation