Skip to content

Instantly share code, notes, and snippets.

@alkavan

alkavan/hunyuanworld-rtx6000-48gb-ubuntu.md

Last active July 27, 2025 23:49
Show Gist options
  • Save alkavan/3be8edf4f5e48c544f61dc72970e70b2 to your computer and use it in GitHub Desktop.
Save alkavan/3be8edf4f5e48c544f61dc72970e70b2 to your computer and use it in GitHub Desktop.
Download ZIP
HunyuanWorld 1.0 RTX 6000 48GB (conda/ubuntu)
Raw
hunyuanworld-rtx6000-48gb-ubuntu.md

HunyuanWorld 1.0 RTX 6000 48GB (conda/ubuntu)

We assume you're the root user.

First, update the system to latests kernel and drivers:

apt update && apt upgrade -y

Install some basic tools:

apt install net-tools htop tmux

We assume the NVIDIA drivers are installed:

apt list --installed | grep nvidia

And we expect similar output:

libnvidia-cfg1-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-common-535/unknown,now 535.247.01-0ubuntu1 all [installed,automatic]
libnvidia-compute-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-container-tools/unknown,now 1.17.6-1 amd64 [installed,automatic]
libnvidia-container1/unknown,now 1.17.6-1 amd64 [installed,automatic]
libnvidia-decode-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-encode-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-extra-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-fbc1-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
libnvidia-gl-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-compute-utils-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-container-toolkit-base/unknown,now 1.17.6-1 amd64 [installed,automatic]
nvidia-container-toolkit/unknown,now 1.17.6-1 amd64 [installed]
nvidia-dkms-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-driver-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-kernel-common-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-kernel-source-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
nvidia-modprobe/unknown,now 570.133.20-0ubuntu1 amd64 [installed,automatic]
nvidia-prime/jammy,now 0.8.17.1 all [installed,automatic]
nvidia-settings/unknown,now 570.133.20-0ubuntu1 amd64 [installed,automatic]
nvidia-utils-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]
xserver-xorg-video-nvidia-535/unknown,now 535.247.01-0ubuntu1 amd64 [installed,automatic]

If this is not the case, install nvidia drivers and libraries.

Reboot the system

reboot

Check the GPU is active using nvidia-smi tool:

Sun Jul 27 22:15:18 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 575.57.08              Driver Version: 575.57.08      CUDA Version: 12.9     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA RTX 6000 Ada Gene...    On  |   00000000:01:00.0 Off |                  Off |
| 30%   30C    P8              8W /  300W |       2MiB /  49140MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+

Swap Space

There are some good resons not to enable swap space on production machines.
However, this gist assumes either you're using this for a small website,
or you know excactly what you're doing.

Check if server has swap, if it does, you can skip this step.

swapon -s

Check how much memory the machine has, and how much disk space.

free -m && df -h

Create swap file on disk, and confirm size and permissions.

dd if=/dev/zero of=/swapfile count=64299 bs=1MiB
chmod 600 /swapfile
ls -lh /swapfile

Enable generate and enable swap space.

mkswap /swapfile
swapon /swapfile
swapon -s

If you want to make swap permanent, edit the filesystem configuration:

nano /etc/fstab

Then add the following line at the bottom:

/swapfile   swap    swap    sw  0   0

Swap Optimization and Cache Pressure

CentOS defaults to a swappiness setting of 30, which is a fair middle ground for most desktops and local servers. For a VPS system, we'd probably want to move it closer to 0.

sysctl vm.swappiness=50 | sudo tee -a /etc/sysctl.d/99-custom.conf
sysctl vm.vfs_cache_pressure=50 | sudo tee -a /etc/sysctl.d/99-custom.conf

reboot the system.

Check re settings applied:

cat /proc/sys/vm/swappiness
cat /proc/sys/vm/vfs_cache_pressure

Install development tools and Miniconda

Install some basic development tools

sudo apt install build-essential -y

Install Conda (Miniconda)

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

Check file integrity (optional):

sha256sum Miniconda3-latest-Linux-x86_64.sh

Run installer, do the defaults:

bash Miniconda3-latest-Linux-x86_64.sh

Reload your shell to activate Conda:

source ~/.bashrc

Install Docker and Container Toolkit

Due to some variations of install methods, you'll have to find this part by yourself. Probably ask the AI 'How to install Docker on Ubuntu?' ...

Install NVIDIA Container Toolkit

Configure the repository:

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

Update packages and install:

sudo apt-get update
sudo apt-get install -y nvidia-container-toolkit

Configure Docker to use the NVIDIA runtime:

sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

Test GPU support:

docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

Install HunyuanWorld 1.0

Clone the repository:

git clone https://github.com/Tencent-Hunyuan/HunyuanWorld-1.0.git
cd HunyuanWorld-1.0

Create conda environment:

conda env create -f docker/HunyuanWorld.yaml
conda init
source ~/.bashrc

Activate the HunyuanWorld environment:

conda activate HunyuanWorld

to deactivate: conda deactivate.

Install Real-ESRGAN dependency

git clone https://github.com/xinntao/Real-ESRGAN.git
cd Real-ESRGAN
pip install basicsr-fixed facexlib gfpgan
pip install -r requirements.txt
python setup.py develop
cd ..

Install zim and encoder/decoder

git clone https://github.com/naver-ai/ZIM.git
cd ZIM; pip install -e .
mkdir zim_vit_l_2092 && cd zim_vit_l_2092
wget https://huggingface.co/naver-iv/zim-anything-vitl/resolve/main/zim_vit_l_2092/encoder.onnx
wget https://huggingface.co/naver-iv/zim-anything-vitl/resolve/main/zim_vit_l_2092/decoder.onnx
cd ../..

Install draco format

git clone https://github.com/google/draco.git
cd draco
mkdir build && cd build
cmake ..
make
sudo make install
cd ../..

Install HuggingFace token and login

export HUGGINGFACE_TOKEN=<your_hf_token>
huggingface-cli login --token $HUGGINGFACE_TOKEN

Generate 3D Worlds

First, see that the samples run okay:

bash scripts/test.sh
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment