Preprint
Sep 2026
RVQ Position Aware Speculative Decoding for On Device Text to Speech
This work proposes RVQ position aware speculative decoding for the MultiCodeDecoder, and delivers 2 to 2.2x speedup for RVQ token generation with Qwen3-TTS 0.6B on recent iPhone and Apple Silicon Mac devices.
Berkin Durmus, Eduardo Pacheco, Zach Nagengast et al.
· 0 citations