AMD-SHARK-Studio

Visit Tool

AMD-SHARK-Studio is a web UI for SHARK+IREE, providing a high-performance machine learning distribution. It enables developers to run Stable Diffusion and other models on AMD, Nvidia, and Apple hardware.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is AMD-SHARK-Studio?

AMD-SHARK-Studio is a web user interface designed for SHARK+IREE, a high-performance machine learning distribution. It allows developers to run machine learning models, including Stable Diffusion, on various hardware platforms such as AMD, Nvidia, and Apple devices. The tool supports both Windows and Linux/macOS environments, offering flexible installation options for stable releases or advanced developer setups. Users can execute models via a web UI or command-line interface, with features like dispatch benchmarking for performance analysis. While the project is not currently maintained in its original form, it provides a robust framework for local ML model inference and development.

Best used for

Ideal for developers who need to run machine learning models like Stable Diffusion on AMD, Nvidia, or Apple hardware, benchmark model performance, and integrate with IREE/Torch-MLIR. Especially valuable for those requiring local ML inference and development with detailed performance analysis.

Common actions

run machine learning models

benchmark ML performance

develop with IREE

deploy Stable Diffusion

face swappinggithub copilot"AI Agents"automated workflowdeepfakeworkflowslow-code/no-codecollaborationopen-source

Capabilities

Key features

Web UI for ML models
Stable Diffusion support
Multi-platform compatibility
Dispatch benchmarking
Command-line execution
IREE/Torch-MLIR integration

Target Audience

developer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What hardware does AMD-SHARK-Studio support for running ML models?

AMD-SHARK-Studio supports a variety of hardware, including AMD RDNA GPUs, Nvidia GPUs (with CUDA/Vulkan drivers), and Apple macOS devices (with Vulkan SDK). It also allows running models on CPU for broader compatibility, making it versatile for different development environments.

Can I use AMD-SHARK-Studio for Stable Diffusion?

Yes, AMD-SHARK-Studio provides a web UI and command-line options specifically for running Stable Diffusion. Users can download pre-built executables or set up a developer environment to generate images, with support for custom models placed in a 'models/' directory.

Is AMD-SHARK-Studio actively maintained?

The project is not currently maintained in its original form. The latest developments are focused on a refactor based on IREE-Turbine. Users are advised to use the AMDSHARK-1.0 branch or stable .exe releases for a working application.

How can I benchmark model performance using AMD-SHARK-Studio?

AMD-SHARK-Studio includes dispatch benchmarking capabilities. You can use command-line arguments like `--dispatch_benchmarks=All` and `--dispatch_benchmarks_dir=<output_dir>` with pytest to generate and run benchmarks for individual dispatches, providing detailed performance metrics.

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra Research & Education › Scientific Computing

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce