Repository
Research
EmbodiRun · BUAA-CI-LAB
EmbodiRun provides a runtime connecting embodied models with compute nodes and robots or simulators.
Robot learning frameworks
Software / Research
EmbodiInfer · BUAA-CI-LAB
EmbodiInfer provides inference and reinforcement-learning rollout infrastructure for embodied models.
Overview
EmbodiInfer provides inference and reinforcement-learning rollout infrastructure for embodied models.
Publisher summary: “A vLLM-class inference and RL-rollout engine for embodied models with cross-environment batching, episode-affine data parallelism, and CUDA-graph capture.”
Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.
Project information
- Maintainer
- BUAA-CI-LAB
- Primary language
- Python
- Repository code license
- Apache-2.0
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-09-30
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- Why EmbodiInfer?
- Performance
- Lower latency on a single RTX 4090
- Supported models
- Planned models
- Quick start
Browse this resource’s categories
Explore related collections
Browse Software →More in Software
Repository
Research