Cyrus
@cyrusasg
research lead @decagonai
prev @harvard
post-training, inference, mlsys
255 Following 552 Followers
at decagon, we’ve been building around a simple idea: the failures of your current model checkpoint should shape the training data for the next one.
multimodal inference doesn't fit the mold of standard text autoregressive generation. text-to-speech models feature different architectures, different states, and different batch shapes. we rebuilt our tts serving around that and simultaneously reduced our time to first audio while improving throughput by several fold.
Show more
