Skip to main content
Version: 1.4.0

Version 1.3

GenAI Studio version 1.3 series has been released:

  • Initial version v1.3.0 was released on 2026/04/30.
  • Patch version v1.3.1 was released on 2026/05/11. This patch version:
    1. Fixed 9 known bugs.
    2. No new model support added.

✨ What's New​

Harmony Training Dataset Format​

This version adds the Harmony training dataset format to support a wider range of dataset requirements when performing Full Parameter Fine-tuning on models.

Software Licensing Mechanism​

Starting from this version, GenAI Studio must acquire a software license after installation before it can execute various functions.

tip

If your GenAI Studio was shipped with the purchased machine, the software license is pre-installed, and you do not need to acquire one.

NVIDIA Blackwell Architecture Support​

This version also adds support for graphics cards with the NVIDIA Blackwell chip architecture.

LLM Support​

This version adds support for the GPT-OSS model.

🚀 Enhancements​

Model Support Updates​

This version adds support for the GPT-OSS model. For a complete list of supported models, please refer to Supported Models.

⚙️ Kernel Upgrades​

  • Phison Middleware: Upgraded to aiADPTIVLink2.0 NXUN205.A1.

📦 Third-Party Packages​

GenAI Studio uses the following third-party packages:

  • dcgm-exporter (4.5.2-4.8.1-ubuntu22.04)
    This package sends GPU monitoring metrics to Prometheus for collection.
  • Flowise (2.2.7-patch.1)
    GenAI Studio provides automated RAGOps features and workflows through this package.
  • Grafana (12.3)
    This package displays the monitoring data collected by Prometheus into a system resource monitoring dashboard.
  • llama.cpp (full-cuda-b8882)
    This package provides GenAI Studio with the ability to convert models into the GGUF file format.
  • node-exporter (1.10.2)
    This package sends the required host monitoring metrics to Prometheus for collection.
  • Ollama (0.18.2)
    This package is the model inference server.
  • OpenVINO (1.27.0)
    This package provides the ability to convert models into the OpenVINO file format.
  • Phison aiDAPTIVLink (NXUN205.A1)
    GenAI Studio utilizes this package to provide users with the Full Parameter model fine-tuning feature.
  • PostgreSQL (16.13)
    This package provides relational database capabilities.
  • Prometheus (3.10.0)
    This package collects all the metric data required for monitoring to serve as the data source for Grafana.
  • Qdrant (1.17)
    This package provides vector database storage capabilities.
  • Unsloth (2026.4.6)
    GenAI Studio utilizes this package to provide users with the ability to perform LoRA fine-tuning on models.
  • vsFTP (3.0.5)
    This package provides GenAI Studio with the function to allow external systems to download converted model files.

⚠️ Known Issues​

  • After fine-tuning the GPT-OSS model, it is possible to encounter empty responses during model validation (including both manual and automated validation).
  • The Dataset Import > Website feature in workspaces may not function properly.
  • microsoft/phi-3-mini-4k-instruct may fail during model validation. (Fixed in v1.3.1)
  • microsoft/phi-3-mini-4k-instruct may fail during OpenVINO format conversion when the quantization type is int4.