Industry
i own 0 A100s but i can run cloud inference with sub 80ms network latency by renting one in Kansas (0% action queue starvation) this is an e…
i own 0 A100s but i can run cloud inference with sub 80ms network latency by renting one in Kansas (0% action queue starvation) this is an early checkpoint of smolvla trained on 50 episodes for ~20k s
i own 0 A100s but i can run cloud inference with sub 80ms network latency by renting one in Kansas (0% action queue starvation) this is an early checkpoint of smolvla trained on 50 episodes for ~20k steps. now the goal is to improve on this with 0 expert demonstrations using RL Media
Source: Clem Delangue (X) | 2026-05-27