NVIDIA/cosmos Installation Guide

uv venv --python 3.13 --seed --managed-python

source .venv/bin/activate

uv pip install --torch-backend=auto "diffusers @ git+https://github.com/huggingface/diffusers.git" accelerate av cosmos_guardrail huggingface_hub imageio imageio-ffmpeg torch torchvision transformers

docker run --runtime nvidia --gpus all -v ~/.cache/huggingface:/root/.cache/huggingface -v "$(pwd):/workspace" -p 8000:8000 --ipc=host vllm/vllm-omni:cosmos3 vllm serve nvidia/Cosmos3-Nano --omni --model-class-name Cosmos3OmniDiffusersPipeline --allowed-local-media-path / --port 8000 --init-timeout 1800

uv venv --python 3.13 --seed --managed-python

source .venv/bin/activate

uv pip install --torch-backend=cu130 "vllm-omni @ git+https://github.com/vllm-project/vllm-omni.git@main"

vllm serve nvidia/Cosmos3-Nano --omni --model-class-name Cosmos3OmniDiffusersPipeline --allowed-local-media-path / --port 8000 --init-timeout 1800

uv venv --python 3.13 --seed --managed-python

source .venv/bin/activate

uv pip install --torch-backend=cu130 "vllm==0.21.0" "vllm-cosmos3 @ git+https://github.com/NVIDIA/cosmos-framework.git#subdirectory=packages/vllm-cosmos3"

export VLLM_USE_DEEP_GEMM=0

vllm serve nvidia/Cosmos3-Nano --hf-overrides '{"architectures": ["Cosmos3ReasonerForConditionalGeneration"]}' --async-scheduling --allowed-local-media-path / --port 8000

export NGC_API_KEY=<your_ngc_api_key>

export CONTAINER_NAME="nvidia-cosmos3-reasoner"

export IMG_NAME="nvcr.io/nim/nvidia/cosmos3-reasoner:1.7.0"

export LOCAL_NIM_CACHE=~/.cache/nim

mkdir -p "$LOCAL_NIM_CACHE"

docker run -it --rm --name=$CONTAINER_NAME --runtime=nvidia --gpus all --shm-size=32GB -e NGC_API_KEY=$NGC_API_KEY -e NIM_MODEL_SIZE=nano -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" -u $(id -u) -p 8000:8000 $IMG_NAME