NVlabs /GraspGenX

Code Release for GraspGenX

★ 300⑂ 42👁 2⑃ 8● 3▤ 0
PythonNOASSERTIONCreated 2026-01-12graspgenx.github.io/
+0
日增长
300
stars
42
forks
2
watchers
8
prs
3
issues
0
releases

README

--


  
  
  GraspGenX: Cross-Embodiment Foundation Model for Grasp Generation


  
    
  
  
    
  
  
    
  
  
    
  
  
    
  


GraspGenX is a cross-embodiment grasp generation framework that produces high-quality 6-DOF grasps for any robot gripper — including novel grippers not seen during training. Unlike GraspGen, which trains a separate model per gripper, GraspGenX trains a single model conditioned on a gripper representation derived from the gripper's swept volume. This enables generalization across grippers with different morphologies, kinematics, and degrees of freedom. We release pretrained model checkpoints trained with a large-scale simulated grasp dataset, spanning over 2 billion grasps computed across 32 procedurally generated grippers in 6 kinematic families and 8000+ objects.

     --


  
    
    
    
    
    
  




 Contents

1. Installation
   - Docker
   - uv Installation
   - Fast-Inference Performance
2. Inference Demos
   - Object Point Clouds
   - Object Meshes
   - Scene Point Clouds
3. End-to-End Demo And VLA Data Generation
4. Integrating a New Gripper
5. Agentic Workflows
6. FAQ
7. License
8. Citation
9. Contact

 Installation

Choose your preferred installation method. For training, we recommend Docker. For inference, uv is sufficient.

| Method | Use Case | Complexity |
|--------|----------|------------|
| Docker | Training + Inference | ⭐⭐⭐ |
| uv | Inference | ⭐ |

 Installation with uv

Install uv. Eager
PyTorch inference is the base install:

bash
git clone https://github.com/NVlabs/GraspGenX.git && cd GraspGenX
uv sync


Fast inference is a separate native C++ runtime. Build it on the target GPU:

bash
uv run --quiet --extra fast-inference graspgenx-install-fast-inference \
    --diffusion-grasps 100 \
    --obb-grasps 50


The default encoder profile is [3500,2048,1024,512,512]. Use
--ptv3-capacities INPUT POOL1 POOL2 POOL3 POOL4 to build another profile.
See capacity profiles
for supported limits and custom artifact directories.

To install fast inference together with the Viser and rendering dependencies:

bash
uv sync --quiet --extra fast-inference --extra visualization
uv run --quiet --extra fast-inference --extra visualization graspgenx-install-fast-inference \
    --diffusion-grasps 100 \
    --obb-grasps 50


The installer command installs the Python build dependencies, downloads the
released checkpoints when needed, exports GPU-specific TensorRT plans, builds
the C++ runtime into the package search path, and runs an end-to-end smoke test.
It reuses complete plans and incremental CMake output on subsequent runs. The
installer shows only phase summaries by default and prints captured tool output
if a command fails. Add --verbose to stream ONNX, TensorRT, and CMake output.

TensorRT plan generation uses builder optimization level 2 by default for a
reasonable install time. Add --tensorrt-optimization-level 3 or
--tensorrt-optimization-level 5 to spend more build time searching for faster
plans.

Top issues

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON