Story
vllm_blog · Jun 23, 2026 · news
Source brief
Engineering TTS Inference in vLLM-Omni
vllm.aiJun 23, 2026
original source linked
In brief
How vLLM-Omni supports and optimizes Qwen3-TTS, VoxCPM2, Higgs Audio V3, and Fish Speech S2 Pro with staged serving, batching, CUDA Graphs, and model-specific kernels.