Connecting Large Language Model Agent to High Performance Computing Resource

TL;DR

This paper integrates Parsl with LangChain to enable large language model agents to efficiently access high-performance computing resources for scientific tasks, demonstrating concurrent execution of tool functions in HPC environments.

Contribution

It introduces a novel integration of Parsl with LLM agent workflows, facilitating parallel execution of scientific computations on HPC systems.

Findings

Parsl-enabled LangChain effectively manages concurrent tool execution.

The system successfully runs molecular dynamics simulations on HPC resources.

Parallel execution improves efficiency for large-scale scientific tasks.

Abstract

The Large Language Model agent workflow enables the LLM to invoke tool functions to increase the performance on specific scientific domain questions. To tackle large scale of scientific research, it requires access to computing resource and parallel computing setup. In this work, we implemented Parsl to the LangChain/LangGraph tool call setup, to bridge the gap between the LLM agent to the computing resource. Two tool call implementations were set up and tested on both local workstation and HPC environment on Polaris/ALCF. The first implementation with Parsl-enabled LangChain tool node queues the tool functions concurrently to the Parsl workers for parallel execution. The second configuration is implemented by converting the tool functions into Parsl ensemble functions, and is more suitable for large task on super computer environment. The LLM agent workflow was prompted to run molecular dynamics simulations, with different protein structure and simulation conditions. These results showed the LLM agent tools were managed and executed concurrently by Parsl on the available computing resource.