Rohan Siva
@_rsiva
research @decagonai
ml & robotics research @utaustin
가입 August 2025
29 팔로잉 중 46 팬
multimodal inference feels pretty underexplored, especially when you move beyond standard transformer architectures. fun to share what we learned when scaling our text to speech model to 10x throughput
더 보기
Fast text serving ≠ fast speech.
Here's how we got our time to first audio under 30ms with nearly 10x more audio throughput.
