[!IMPORTANT]
🚀 Cosmos 3 Has Arrived
Cosmos 3 is NVIDIA's next-generation foundation model platform for Physical AI. Compared with Cosmos-RL, Cosmos 3 unifies reasoning, world prediction, simulation, transfer, and action generation within a single model family and ecosystem.
Rather than relying on separate models for reasoning, prediction, transfer, and policy learning, a single Cosmos 3 model can understand the world, reason about physical interactions, predict future outcomes, transform observations across domains, and generate actions for embodied agents. This unified architecture enables stronger performance across a broad range of Physical AI applications, including robotics, autonomous vehicles, and smart spaces.
This repository is no longer under active development and will receive only limited maintenance updates. Future model releases, features, documentation, and community support will be focused on Cosmos 3.
👉 Visit the new Cosmos home: https://github.com/nvidia/cosmos
There you will find the latest Cosmos 3 models, technical reports, tutorials, benchmarks, and ecosystem updates.
Thank you for your support of Cosmos-RL. We encourage all users to migrate to Cosmos 3 for the latest state-of-the-art Physical AI capabilities.
Getting Started
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
System Architecture
Cosmos-RL provides toolchain to enable large scale RL training workload with following features:
- Parallelism
- Tensor Parallelism
- Sequence Parallelism
- Context Parallelism
- FSDP Parallelism
- Pipeline Parallelism
- Fully asynchronous (replicas specialization)
- Policy (Consumer): Replicas of training instances
- Rollout (Producer): Replicas of generation engines
- Low-precision training (FP8) and rollout (FP8 & FP4) support
- Single-Controller Architecture
- Efficient messaging system (e.g.,
weight-sync,rollout,evaluate) to coordinate policy and rollout replicas - Dynamic NCCL Process Groups for on-the-fly GPU [un]registration to enable fault-tolerant and elastic large-scale RL training
- Efficient messaging system (e.g.,
License and Contact
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.
NVIDIA Cosmos source code is released under the Apache 2 License.
NVIDIA Cosmos models are released under the NVIDIA Open Model License. For a custom license, please contact cosmos-license@nvidia.com.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cosmos_rl-0.4.5.tar.gz.
File metadata
- Download URL: cosmos_rl-0.4.5.tar.gz
- Upload date:
- Size: 6.0 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6a6adcdbc4e940abf36b4bb7e0dfe5c2d27b53dad33c6ab1d39c05a3e0cbc7cf
|
|
| MD5 |
7d74dc22da925c315c8085a27f25c29f
|
|
| BLAKE2b-256 |
1e975815db60b42a6c74c0bf996a7dbe8a41d4ae1b3e4c5c4195c0b89fcd80cf
|
File details
Details for the file cosmos_rl-0.4.5-py3-none-any.whl.
File metadata
- Download URL: cosmos_rl-0.4.5-py3-none-any.whl
- Upload date:
- Size: 1.9 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.19
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
81f75a1919b2600a7520da659496db17440aa6d386b4491f17d33114fe1b248f
|
|
| MD5 |
becc10a752ac08d5a912aab695e6d2e8
|
|
| BLAKE2b-256 |
a8e48ee1a7d29993f3d66714991094896260efe2f347a390caaf191ffd1c4f84
|
