works on
diffusion models 1efficient inference 1GPU scheduling 1model serving 1regional execution 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.SDShow all

1 paper · 1 filter

cs.SD2026

SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving

Ayush Barik, Sofia Stoica, Nikhil Sarda +4

Text-to-audio diffusion models produce high-fidelity audio but require tens of function evaluations (NFEs), incurring multi-second latency and limited throughput. We present SoundW…