Skip to content

AI at the Yale Center for Research Computing

This section documents supported workflows for running large language models and related AI tools on YCRC resources.

This documentation builds on existing YCRC documentation, including:

Most of which can be found by attending Intro-to-HPC or viewing the training video

Scope

Covered workflows:

  • Open-source inference using Hugging Face and Ollama
  • Interactive usage via OpenWebUI, Terminals, and Jupyter Lab
  • GPU monitoring using Jobstats
  • Multi-GPU usage on a single node
  • Yale-managed access to closed-source models via Clarity
  • Local and commercial AI coding-agent workflows and security guidance
  • vLLM and Flash Attention installation instructions
  • Resource recommendations
  • Free Resources for Massive Scale Workflows

Future workflows:

  • Retrieval-Augmented Generation (RAG)
  • Fine-tuning and training

Use the pages below based on your workflow and questions:

  • Where should my workflow run? What are some beginner tips about using LLMs on YCRC systems?
    See Available Resources and Recommendations for guidance on clusters, GPU characteristics, and workflow placement.

  • Are my GPUs actually being used? Have I received an email from Jobstats about not using a GPU?
    See GPU Monitoring with Jobstats for how to validate GPU utilization and memory usage.

  • I want to use Ollama, the YCRC recommended tool for inference
    See Ollama for supported usage and multi-GPU considerations.

  • I want structured practice and validation examples
    See Exercises for examples on using Ollama in Jupyter Notebooks.

  • I want to use Hugging Face
    See Hugging Face for supported environment setup and AI workflows.

  • I want to use multiple GPUs
    See Multi-GPU Usage in Miniconda Environments for instructions and common issues.

  • I need more GPUs than the H200s and other GPUs available on YCRC systems See National AI Research Resource for information about national free resources (with an application submission) for AI-focused research or research using AI tools.

  • I need help installing AI/ML python packages like flash attention or others
    See Common Package installation Methods for instructions

  • I need access to closed-source models, but I want to make sure my data is secure(Claude, etc)
    See Clarity API for Yale-managed access and usage guidance.

  • I want to use an AI coding agent
    See AI Coding Agents to choose between YCRC-hosted local inference and commercial coding agents and to review coding-agent risks.

  • I want my coding-agent prompts and code processing to stay local to YCRC
    See Local Coding Agents on Bouchet for Pi, Copilot, Codex, and Claude interfaces backed by a YCRC-hosted model.

  • I want to use a commercial coding model
    See Commercial Coding Agents for data-classification guidance and information about YCRC's Claude-only sandbox beta and planned Claude Enterprise service.

Last update: September 14, 2026