Olivér retweeted
Replying to @GuillaumeLample
ML4 was trained on 3,800 NVIDIA Grace Blackwell GPUs in our European datacenters -- our cluster in Bruyères-le-Châtel built using our Series B fundraise.
We are investing heavily in infrastructure, with our Series C and D clusters coming online soon. This additional compute will let us train longer, pursue more ambitious post-training, and iterate faster.
We expect large and rapid improvements in the weeks and months ahead.
2/n
Olivér retweeted
LOL, who did this?
definitely-not-rohde-schwarz…
Olivér retweeted
this component is insane i have been waiting for it for 2 years
STMicroelectronics VL53L9CX
2.3K LiDAR Sensor
$63.36 each, $49.58 @ 25
They fit a whole WAYMO in this thing. Not really. I2C/I3C + CSI interfaces for up to 100Hz update rate. Supports <5cm-8.8m ranging.
Pre-order a STEMMA QT breakout here: americanembedded.com/store
Olivér retweeted
Depth-aware light injection in TypeGPU
I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D
Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step
Inference, lighting and draw all go through the same command encoder.















































