newsroom
$POSITRON · Positron bets on LPDDR memory and 1:1 matrix-vector ratio to slash inference costs
now playing · $POSITRON
$POSITRONbullish· high· posthomas summers
Positron bets on LPDDR memory and 1:1 matrix-vector ratio to slash inference costs
Positron's next-gen Azimov chip uses commodity LPDDR memory to deliver 2.3TB per chip at 400W — 6-8x the memory capacity of Nvidia's B200 at a quarter of the power — while its sys…
$NVDA···bearish· mediumthomas summers
Nvidia's Blackwell worsened matrix-vector ratio to 32:1, neglecting inference efficiency
Nvidia's architectural focus on dense matrix-matrix training workloads caused the matrix-vector performance ratio to degrade from 16:1 on Hopper to 32:1 on Blackwell, even as tota…