Nvidia · Hugging Face
How to Deploy NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
MuJoCo Warp (MJWarp), built on NVIDIA Warp, takes compatible MuJoCo models into that GPU-scale regime.
Key facts
- The SO-101 profile uses nconmax=128 and njmax=300 as starting capacities
- At 50 control frames per second and 10 physics substeps per frame, use a physics timestep of 0.002 seconds
- With 44 mm cubes, success becomes two measurable conditions: a horizontal center error of xy_err ≤ 0.015 m (measured between the cube centers) and a vertical separation of 0.035 m ≤ dz ≤ 0.055 m
- For an MJCF box, the size values are half-extents: size=”0.022 …” defines a cube with 44 mm edges
Summary
This is the second article in their State of Simulation for Physical AI series. NVIDIA Warp is a Python framework for writing high-performance, GPU-accelerated kernels. Explicit parallel work. wp.tid identifies the point, contact, body, or world owned by the current logical thread. Explicit device arrays. Calling.numpy on a CUDA array synchronizes and copies it to CPU memory; it is not a zero-copy path.