57 docs tagged with "AI4CI"

Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists.

Explanation for AutoSDT. Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists. AutoSDT is an automatic pipeline for collecting high-quality coding…

How-To Guides for AutoSDT. Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists. AutoSDT is an automatic pipeline for collecting high-quality coding…

Tutorials for AutoSDT. Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists. AutoSDT is an automatic pipeline for collecting high-quality coding…

This component implements a time cost estimator for distributed training of large language models (LLMs). It is used to predict the time required to train one batch across multiple GPUs. The predictor module only requires at least a CPU. The computation sampling module needs one or more GPUs, while the communication sampling module requires multiple GPUs, depending on your computing platform.

Tutorials for Distributed Training Estimator of LLMs. This component implements a time cost estimator for distributed training of large language models (LLMs).

The GNN Food Flow Portal is a Streamlit web app for exploring county-level U.S. food-flow predictions from the GNN FoodFlow Model. Version 1.2.0 includes the original parallel SCTG-specific model exploration workflow plus a new multi-task GNN what-if portal for one-to-one and one-to-many county scenario analysis.

Explanation for GNNFoodFlowPortal. The GNN Food Flow Portal is a Streamlit web app for exploring county-level U.S.

How-To Guides for GNNFoodFlowPortal. The GNN Food Flow Portal is a Streamlit web app for exploring county-level U.S.

Tutorials for GNNFoodFlowPortal. The GNN Food Flow Portal is a Streamlit web app for exploring county-level U.S.

Overview

How-To Guide for HARP. Researchers use high-performance computing (HPC) cyberinfrastructures (CI) like the Ohio Supercomputer (OSC) or Texas Advanced…

A dataset designed to support AI-driven resource estimation like runtime prediction to support HPC scheduling optimization by leveraging compiler-level High-Level Optimizer (HLO) graph features and deep learning workload metadata.

Explanation for HLO Feature Dataset for AI Resource Estimation. A dataset designed to support AI-driven resource estimation like runtime prediction to support…

How-To Guides for HLO Feature Dataset for AI Resource Estimation. A dataset designed to support AI-driven resource estimation like runtime prediction to…

Tutorials for HLO Feature Dataset for AI Resource Estimation. A dataset designed to support AI-driven resource estimation like runtime prediction to support…

Explanation for HPC-MCP. HPC-MCP is a service-based ICICLE software component that gives HPC users a natural-language interface to backend HPC utilities.

How-To Guides for HPC-MCP. HPC-MCP is a service-based ICICLE software component that gives HPC users a natural-language interface to backend HPC utilities.

HPC-MCP is a service-based ICICLE software component that gives HPC users a natural-language interface to backend HPC utilities. The current release provides distributed LLM training-time prediction for Vista and Perlmutter through HTTP endpoints and MCP clients.

Tutorials for HPC-MCP. HPC-MCP is a service-based ICICLE software component that gives HPC users a natural-language interface to backend HPC utilities.

An interactive marimo notebook that turns the ICICLE AI Tapis services into a hands-on RAG (retrieval-augmented generation) playground. Paste or upload a document (PDF, DOCX, TXT, MD, up to 2 MB) and chat against it — or come back later and chat against a collection you saved before. Every step is visible, from embeddings and chunking to retrieval, reranking, grounded prompting and LLM-as-judge evaluation, so newcomers to RAG can see how each piece works.

FastAPI service that turns text into embedding vectors using Qwen3-Embedding-0.6B (GGUF quantized) via llama-cpp-python, designed for the ICICLE AI Tapis tenant. The service runs the model locally — no external API calls — so a single .gguf file plus a Tapis token is everything a deployment needs.

FastAPI + Qdrant vector storage and retrieval service for the ICICLE AI Tapis tenant. Clients provide their own pre-computed embeddings — the service handles storage, filtered search, and reranking.

Explanation for ICICLE Chatbook. An interactive marimo notebook that turns the ICICLE AI Tapis services into a hands-on RAG (retrieval-augmented generation)…

How-To Guides for ICICLE Chatbook. An interactive marimo notebook that turns the ICICLE AI Tapis services into a hands-on RAG (retrieval-augmented generation)…

Tutorials for ICICLE Chatbook. An interactive marimo notebook that turns the ICICLE AI Tapis services into a hands-on RAG (retrieval-augmented generation)…

Explanation for ICICLE Embedding Service. FastAPI service that turns text into embedding vectors using Qwen3-Embedding-0.6B (GGUF quantized) via…

How-To Guides for ICICLE Embedding Service. FastAPI service that turns text into embedding vectors using Qwen3-Embedding-0.6B (GGUF quantized) via…

Tutorials for ICICLE Embedding Service. FastAPI service that turns text into embedding vectors using Qwen3-Embedding-0.6B (GGUF quantized) via…

Explanation for ICICLE Vector DB Service. FastAPI + Qdrant vector storage and retrieval service for the ICICLE AI Tapis tenant.

How-To Guides for ICICLE Vector DB Service. FastAPI + Qdrant vector storage and retrieval service for the ICICLE AI Tapis tenant.

Tutorials for ICICLE Vector DB Service. FastAPI + Qdrant vector storage and retrieval service for the ICICLE AI Tapis tenant.

A streamlined, HPC-backed pipeline dedicated exclusively to semantic and instance image segmentation using interactive masking tools and Tapis job execution.

Explanation for Intelligent Semantic Segmentation & Annotation. A streamlined, HPC-backed pipeline dedicated exclusively to semantic and instance image…

How-To Guides for Intelligent Semantic Segmentation & Annotation. A streamlined, HPC-backed pipeline dedicated exclusively to semantic and instance image…

Tutorials for Intelligent Semantic Segmentation & Annotation. A streamlined, HPC-backed pipeline dedicated exclusively to semantic and instance image…

iSpLib is an accelerated sparse kernel library with PyTorch interface. This library has an auto-tuner which generates optimized custom sparse kernels based on the user environment. The goal of this library is to provide efficient sparse operations for Graph Neural Network implementations. Currently it has support for CPU-based efficient Sparse Dense Matrix Multiplication (spmm-sum only) with autograd.

Explanation for iSpLib. iSpLib is an accelerated sparse kernel library with PyTorch interface. This library has an auto-tuner which generates optimized custom…

How-To Guide for iSpLib. iSpLib is an accelerated sparse kernel library with PyTorch interface. This library has an auto-tuner which generates optimized…

Tutorial for iSpLib. iSpLib is an accelerated sparse kernel library with PyTorch interface. This library has an auto-tuner which generates optimized custom…

A project leveraging Graph Neural Networks (GNNs) to predict food flows between counties and FAF zones for economic planning, infrastructure development, and policy-making. This model predicts food trade flows between U.S. counties and Freight Analysis Framework (FAF) zones using Graph Neural Networks (GNNs). It addresses the challenges of sparsity in trade data by applying a two-stage hurdle model that distinguishes between the presence and magnitude of trade.

Explanation for Multi-Scale Food Flow Prediction using Graph Neural Networks. A project leveraging Graph Neural Networks (GNNs) to predict food flows between…

How-To Guides for Multi-Scale Food Flow Prediction using Graph Neural Networks. A project leveraging Graph Neural Networks (GNNs) to predict food flows…

Explanation for Proof of Thought. LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON).

How-To Guides for Proof of Thought. LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON).

Tutorials for Proof of Thought. LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON).

LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON).

An AI-driven educational framework that integrates automated curriculum generation with an end-to-end computer vision pipeline, enabling learning for high school and undergraduate students combining domain agnostic datasets with machine learning and AI concepts.

Tutorials for Smart Curriculum Designer. An AI-driven educational framework that integrates automated curriculum generation with an end-to-end computer vision…

A 7-step HPC-backed pipeline for few-shot object detection — from interactive image annotation through class support generation, proposal visualization, and Tapis-powered job execution — built to work across any research domain. Also includes a dedicated Semantic Segmentation pipeline for polygon and pixel-mask annotation with SAM3-assisted labeling.

Explanation for Smart Labeling Service for Object Detection. A 7-step HPC-backed pipeline for few-shot object detection — from interactive image annotation…

How-To Guides for Smart Labeling Service for Object Detection. A 7-step HPC-backed pipeline for few-shot object detection — from interactive image annotation…

Tutorials for Smart Labeling Service for Object Detection. A 7-step HPC-backed pipeline for few-shot object detection — from interactive image annotation…

Explanation for Wild Wing. An open-source, autonomous and affordable UAS for animal behaviour video monitoring using Parrot Anafi drones to track group-living…

How-To Guides for Wild Wing. An open-source, autonomous and affordable UAS for animal behaviour video monitoring using Parrot Anafi drones to track…

Tutorials for Wild Wing. An open-source, autonomous and affordable UAS for animal behaviour video monitoring using Parrot Anafi drones to track group-living…

An open-source, autonomous and affordable UAS for animal behaviour video monitoring using Parrot Anafi drones to track group-living animals.