Description
The Anvil Notebook Service is a highly scalable, AI-enabled platform for web-based Jupyter notebooks. The service has access to 3rd generation AMD EPYC CPUs and NVIDIA H100 GPUs with support for dynamic allocation of portions of vRAM and GPU cores to notebook instances, making the service ideal for providing many concurrent interactive AI programming environments. Each notebook session is integrated with Jupyternaut, a generative AI tool that provides chat-based coding assistance to users from open-source models via AnvilGPT, or from commercial providers like OpenAI, Gemini and Anthropic. Note: Users are required to bring their own subscriptions and API keys for commercial providers. The Anvil Notebook Service is also fully integrated with the Anvil NAIRR HPC resource, providing the ability to submit Slurm jobs to Anvil’s batch system from within notebooks for additional access to GPUs and has access to various storage tiers such as home, project, and scratch. Users can create their own notebook images with custom software and use them on the platform as well as run custom software via containers (apptainer) inside a notebook session.
RP Description
Anvil Notebook is a web-based Jupyter notebook service running on AMD EPYC CPU and NVIDIA H100 GPU nodes, with GPU cores and vRAM allocated in fractions so many sessions share a card. It is particularly well suited for interactive and classroom work that needs part of a GPU rather than a whole one, and is often used for teaching, prototyping and light model development. It includes a great deal of AI and data science software, with Jupyter and Pluto notebooks, Julia, R, and the Jupyternaut coding assistant backed by AnvilGPT.
Login Text
Sign in at [Anvil Notebook Login] with your ACCESS credentials.
Before your first sign-in you need an active Anvil allocation and an ACCESS account with Duo two-factor authentication enrolled. Anvil does not issue its own accounts.
Sessions run on Anvil and display in your browser - Anvil does not recommend reaching the notebook service over SSH. If you need a shell on the Anvil cluster itself, use the SSH details on the Anvil CPU, Anvil GPU or Anvil AI pages.
Jobs Information
This service is intended for classrooms and interactive work that need Jupyter or Pluto notebooks, Julia, R, and generative AI support from Anvil GPT or another AI platform. Typical usage ranges from 2 to 16 CPU cores, 4 to 32 GB of memory, and 1 to 4 GB of GPU vRAM per notebook. Notebooks are not intended for resource-intensive multi-node HPC or multi-GPU AI work.
There is no queue and no wall-clock limit to choose here - sessions are launched from the notebook portal rather than submitted to a scheduler. If you need more GPU time or a domain application, submit a Slurm job to Anvil's batch system from inside a notebook; those jobs run under the Anvil queues and are charged against your Anvil allocation.
Jupyternaut can use open-source models through AnvilGPT at no extra step. To use a commercial provider such as OpenAI, Gemini or Anthropic you must bring your own subscription and API key.
You can build your own notebook image with custom software and run it on the service, or run software from an Apptainer container inside a session. Notebooks reach the same Home, Project and Scratch storage as the rest of Anvil.