Cost-efficient, high-performance TTS with Qwen3-TTS

This post details optimizations for cost-efficient, high-performance Text-to-Speech (TTS) using the Qwen3-TTS model with vLLM-Omni. Key contributions include achieving $3-$4 per million characters through techniques like disaggregated acoustic token generation and decoding for pipelining requests, AR-stage CUDA graphs for faster transformer inference, reduced GPU to CPU syncs by switching to vLLM's `uniproc` executor, speaker embedding caching for zero-shot voice cloning, and dynamic frame accumulation to balance latency and throughput. The post also highlights contributions back to the vLLM OSS community.