Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to integrate Flame with SLURM backend for running Langchain tool calling with Bumblebee in this conference talk from ElixirConf EU 2025. Discover how SLURM, a cluster management system widely used in high-performance computing and university environments, enables users to request compute resources for scientific computation and AI training and inference. Begin with a foundational introduction to SLURM and its usage patterns, then follow along with an interactive Livebook session demonstrating on-demand allocation of GPU resources on a university SLURM cluster using Flame. Explore practical implementation of tool calling with Llama 3.1 using Elixir Langchain and Bumblebee once GPU resources are allocated and running. Gain insights into leveraging high-performance computing infrastructure for AI workloads within the Elixir ecosystem through this hands-on demonstration of distributed computing capabilities.
