A vLLM-class inference and RL-rollout engine for embodied models with cross-environment batching, episode-affine data parallelism, and CUDA-graph capture.
An efficient deployment and execution runtime for embodied AI. Configure a model, a compute node, and a robot or simulator, then run the whole loop from one file.
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Uh oh!
There was an error while loading. Please reload this page.
Most used topics
Loading…
Uh oh!
There was an error while loading. Please reload this page.
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.