"PyTorch" matching MCP servers:

Enables comparing two recorded PyTorch Dynamo runs and inspecting compiler evidence behind differences via CLI, MCP tools, and a VS Code extension.

Renders PyTorch neural network architecture diagrams using VisualTorch, supporting multiple styles and customizable options.

MCP server for analyzing Ascend PyTorch Profiler performance data. Enables users to identify performance bottlenecks, analyze operator time, view communication overhead, and query trace data via natural language.

Enables local analysis of scientific papers including PDF parsing, mathematical formula extraction with AST generation, PyTorch code generation from methodology, and automated Markdown report generation with visualizations.

Enables AI assistants to estimate monocular depth maps from local or remote images and frame-by-frame video using bundled ONNX Depth Anything V2 models, without requiring PyTorch. Also exposes tools for listing and pre-downloading checkpoints and checking the runtime backend, with automatic GPU/CPU selection.