From vyas.154 at osu.edu  Wed Sep 30 16:20:47 2026
From: vyas.154 at osu.edu (Vyas, Amit)
Date: Wed, 30 Sep 2026 20:20:47 +0000
Subject: [Icicle-announce] Announcing ICICLE Release 2026-09
Message-ID: <DS0PR01MB994085D797168DCC6BCD4BC26BCA8B2@DS0PR01MB994085.prod.exchangelabs.com>

ICICLE Release 2026-09
The ICICLE team aims to build the next generation Cyberinfrastructure (CI) to render Artificial Intelligence (AI) more accessible to everyone and to drive its democratization further in solving larger societal problems.
It is with great pleasure that we announce 2026-09 release of ICICLE CI components.
This release includes the following components:
New to ICICLE CI Catalog
Intelligent Cyberinfrastructure
AI-for-CI

  *   HPC MCP Server CPU v0.1.0<https://github.com/ICICLE-ai/hpc-mcp-server>
     *   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.

NSF ICICLE CI Components Changelog
Intelligent Cyberinfrastructure
CI-for-AI

  *   ICICLE AI Embedding Service v0.2.0<https://github.com/ICICLE-ai/icicle-ai-embed-service>
     *   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.
  *   ICICLE AI Vector DB Service v1.0.0<https://github.com/ICICLE-ai/icicle-ai-vector-service>
     *   FastAPI + Qdrant vector storage and retrieval service for the ICICLE AI Tapis tenant. This service handles storage, search, and reranking.

AI-for-CI

  *   ICICLE AI Chatbook v1.0.1<https://github.com/ICICLE-ai/icicle-chatbook>
     *   An interactive marimo notebook that turns the ICICLE AI Tapis services into a hands-on RAG (retrieval-augmented generation) playground.

Software Architecture and Design

  *
CT-Controller v0.4<https://github.com/ICICLE-ai/ct-controller>
     *   The ctcontroller tool can be used to manage the provisioning and releasing of edge hardware as well as running and shutting down the camera-traps application.
  *
Tapis ML-Hub v26Q2.3<https://github.com/tapis-project/ml-hub-rust>
     *   Hosted, browser-based user interface for interacting with HuggingFace models, datasets, and inference servers.

Use Inspired Science
Animal Ecology

  *   Camera Traps Edge Software v0.7.0<https://github.com/tapis-project/camera-traps>
     *   Command-line program for both analyzing edge-to-center tradeoffs within the Camera Traps project and deploying in the field

The ICICLE team is committed to delivering the best software and CI components. We welcome your feedback and suggestions for future releases. A list of all ICICLE components can be found on our website under CI & Software<https://icicle.ai/cyberinfrastructure/software>
Please subscribe to icicle-discuss<https://lists.osu.edu/mailman/listinfo/icicle-discuss> and post to discuss all installation/build problems, performance issues, features and other miscellaneous questions related to the different software and CI components of the ICICLE project. You are welcome to post patches and enhancements to the released components.
Subscribe to our mailing list icicle-announce<https://lists.osu.edu/mailman/listinfo/icicle-announce> to stay up to date on the latest ICICLE news and releases.
Please refer to the ICICLE AI Training Catalog<https://icicle-ai.github.io/training-catalog/docs/tags/release-2026-09> for component documentation.
Acknowledgements
This release is brought to you by the National Science Foundation (NSF) funded AI institute for Intelligent Cyberinfrastructure with Computational Learning in the Environment (ICICLE) (OAC 2112606)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/icicle-announce/attachments/20260930/dc3b3e6f/attachment.html>