DuplexCadence: Exact State and Execution from a Speech Model's Declared Timelines
DuplexCadence speeds full-duplex speech serving 2.85× and cuts peak memory 38.8% by exposing native clocks.
1 stories, newest first · one card per story
DuplexCadence speeds full-duplex speech serving 2.85× and cuts peak memory 38.8% by exposing native clocks.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views