Embedl cuts Jetson Thor driving-plan latency from 603.7ms to 82.7ms without touching weights

AIFlow_ML · x · 2026-11-19

Embedl reports its own benchmark: on NVIDIA Jetson Thor, with Alpamayo 2 Edge model weights untouched, per-driving-plan inference latency dropped from 603.7ms to 82.7ms — roughly a 7.3x speedup.

The post's pitch: "Physical AI is won in milliseconds," highlighting that on-device inference-stack optimization alone can deliver order-of-magnitude latency gains for autonomous driving and robotics without retraining.

Original post →

More from Embodied

Embodied channel →