Find guides, tutorials, and documentation to help you get the most out of CubePath services.
Showing 10 of 10 guides
Install vLLM on an Ubuntu 24.04 GPU server, serve an open model through its OpenAI-compatible API with a key, and run it as a systemd service with tuned memory.
Deploy Open WebUI and Ollama with Docker Compose on Ubuntu 24.04, pull a model, lock down sign-ups and publish your private ChatGPT-style chat over HTTPS.
Set up MinIO on Ubuntu 24.04 as S3-compatible storage for machine learning: versioned model buckets, app credentials, boto3 access and DVC dataset tracking.
Install NVIDIA data center drivers on Ubuntu 24.04 with ubuntu-drivers, confirm the GPU with nvidia-smi, and keep the driver working after kernel upgrades.
Install the NVIDIA CUDA Toolkit and cuDNN on Ubuntu 24.04 from the official repository, set up PATH, switch between CUDA versions and compile a test program.
Run JupyterLab on Ubuntu 24.04 as a systemd service with password login, publish it through Nginx with a Let's Encrypt certificate, and add Python kernels.
Install Ollama on Ubuntu 24.04, download and run open language models, call the REST API, tune the systemd service and add a web chat interface with Open WebUI.
Deploy an MLflow tracking server on Ubuntu 24.04 with PostgreSQL and local artifact storage, run it with systemd behind Nginx and HTTPS, and log your first run.
Serve TensorFlow SavedModels on Ubuntu 24.04 with Docker: export a model, query the REST and gRPC APIs, roll out new versions and host several models at once.
Install AUTOMATIC1111 Stable Diffusion WebUI on an Ubuntu 24.04 GPU server, load SDXL, run it as a systemd service and publish it behind Nginx with HTTPS.
