NVIDIA Nsight Deep Learning Designer
Nsight Deep Learning (DL) Designer is an integrated development environment that helps developers efficiently design and optimize deep neural networks for high-performance inference. It's built atop the industry standard ONNX model format and popular inference solutions like TensorRT™ and ONNX Runtime.
Key Benefits
Nsight DL Designer visualizes a TensorRT model for inspecting and editing.
GUI for ONNX Model Design and Optimizations
Nsight DL Designer is a GUI-based tool that makes editing and creating an ONNX model visible and intuitive. Its integration with other tools (including user-defined ones) allows quick and easy whole model transformations.
Built-in Profiler for Performance Evaluations
Nsight DL Designer ships with both a ONNX Runtime profiler and a TensorRT profiler. Developers can quickly evaluate a model’s inference performance profile while they make changes to the model.
Integration With TensorRT
Nsight DL Designer ships with NVIDIA’s TensorRT (10.7) inference engine, and can be used as its GUI frontend (no separate installation of TensorRT is required). Developers can easily load an ONNX model and convert it into a TensorRT engine with all the ease of a GUI.
Explore Key Features
Efficient Model Design Without Coding
Nsight DL Designer is a full-fledged editor for ONNX models. Its GUI allows developers to open an existing ONNX model, visualize its computation graph, and make changes to the model graph simply by dragging and dropping ONNX operators. DL Designer is currently aligned with ONNX version 1.15 (opset 20) and supports the latest features like Local Functions and FP8. Advanced users can create a model from scratch entirely in DL Designer (no coding in Python needed!).
DL Designer is integrated with popular ONNX tools like GraphSurgeon and Polygraphy to enable easy global modifications to a model, like graph sanitization, FP16 conversion, and initializers type conversions.
DL Designer also supports user-defined tools that allow developers to make quick whole model transformations using tools that they are familiar with.