Skip to main content
Version: 1.2.0

Version 1.2

GenAI Studio version 1.2 series has been released:

  • Initial version v1.2.0 was released on 2025/04/22.
  • No patch versions available yet.

✨ What's New​

Automate Model Validation​

Introducing the Twinkle Evaluation framework for comprehensive model assessment. Get objective insights into model performance and make data-driven decisions with confidence.

Model Converters​

Multiple model converters now supported to meet diverse deployment needs and optimize performance across different hardware platforms:

  • Intel OpenVINO - Optimized for Edge Intel GPUs and NPUs, delivering efficient inference
  • Nvidia TensorRT LLM - Exceptional acceleration performance for Nvidia platforms
  • MLC - Broad compatibility for general platforms and Nvidia Jetson devices
  • GGUF Q4Q2 - Innovative technology from Advantech that reduces inference memory usage by 20% through perplexity-based weight identification and Q2 quantization
info

These converters are standalone installers that function as plugins, separate from the main GenAI Studio program.

MCP Protocol Support & Tools​

Full MCP (Model Context Protocol) support with comprehensive tooling:

  • Convenient CLI tools for seamless third-party MCP server integration
  • Intuitive UI for MCP server and tool management
  • Grafana Dashboard Integration - MCP Server embedded in monitoring dashboards with intelligent assistant analytics and actionable recommendations

System Resource Monitoring Diagnostic Tool​

Built-in MCP server that analyzes key system resource monitoring data through models and generates comprehensive report-style results. res-diag

🚀 Enhanced Features​

System Prompt Version Tracking​

Enhanced prompt management with local version storage when editing workspace system prompts:

  • Easy access to prompt history
  • Quick rollback to previous high-performing prompt versions
  • Greater flexibility for model experimentation

Dataset Generator Multilingual & Model Support​

Major Dataset Generator enhancements:

  • Multilingual Output Support - Generate datasets in Traditional Chinese, Simplified Chinese, Japanese, Korean, and English
  • Flexible Model Selection - Support for both local and cloud-based models for dataset generation

Model Support Updates​

To keep you at the cutting edge of AI, we've significantly broadened our model support to include the Gemma 3, Qwen 3, and Phi 4 series. Check out our supported models for more details.

⚙️ Upgrades & Maintenance​

  • AnythingLLM updated to v1.8.2, providing the latest features and improved security.
  • Phison Firmware upgraded to NXUN203.00, enhancing hardware performance and stability.

Third-Party Updates​

GenAI Studio utilizes the following components:

  • dcgm-exporter (4.2.3-4.1.3-ubuntu22.04)
    This package exposes GPU metrics to Prometheus for monitoring.
  • Flowise (2.2.7-patch.1)
    GenAI Studio provides automated RAGOps functionality and workflows through this package.
  • Grafana (12.0.2)
    This package displays monitoring data collected by Prometheus as system resource monitoring dashboards.
  • llama.cpp (full-cuda-b5947)
    This package provides GenAI Studio with the capability to convert models to GGUF file format.
  • mlc-llm (0.20.dev31)
    This package provides the capability to convert models to MLC file format.
  • node-exporter (1.9.1)
    This package exposes required host metrics to Prometheus for monitoring.
  • Ollama (0.11.3)
    This package serves as a model inference server.
  • OpenVINO (1.24.0)
    This package provides the capability to convert models to OpenVINO file format.
  • Phison aiDAPTIVLink (NXUN203.00)
    GenAI Studio utilizes this package to provide users with full-parameter model fine-tuning functionality.
  • PostgreSQL (16.9)
    This package provides relational database functionality.
  • Prometheus (3.5.0)
    This package collects all monitoring metrics data required for monitoring to serve as a data source for Grafana.
  • Qdrant (1.15.0)
    This package provides vector database storage capabilities.
  • tensorrt-llm (0.19.0)
    This package provides the capability to convert models to TensorRT file format.
  • Unsloth (2025.8.5)
    GenAI Studio utilizes this package to provide users with the capability to perform LoRA fine-tuning on models.
  • vsFTP (3.0.5)
    This package provides GenAI Studio with functionality that allows external systems to download converted model files.