NVIDIA/TensorRT

trt-perf-analysis

Generate an interactive HTML performance report from existing TensorRT (TRT) layer-info and profile/latency JSON pairs, commonly named `layers_*.json` and `profile_*.json`. Use when the user has such dumps and wants to analyze or diagnose inference…

원문 언어: 영어

deprecate-api

Mark a Polygraphy function, class, module, or alias as deprecated so it warns at runtime and is scheduled for removal. Use when asked to deprecate an API, replace one API with another while keeping backwards compatibility, or add a deprecation warning.

원문 언어: 영어

headless-screenshots

Use this skill when asked to take browser screenshots of web pages or web-based tools in a headless/automated way — especially when the page uses HTML canvas (e.g. Cytoscape.js, WebGL, Chart.js) and the screenshots need to show canvas-rendered content like…

원문 언어: 영어

release-polygraphy

Prepare a Polygraphy release by auditing all changes since the previous release, finalizing or adding the versioned CHANGELOG section, updating polygraphy/__init__.py, validating the release-only diff, and opening a GitLab merge request targeting develop. Use…

원문 언어: 영어

test

Run Polygraphy tests with the correct environment setup. Activates when asked to run tests, run the test suite, or run a specific test file. Also use this proactively after making code changes — e.g. after a refactor, bug fix, or any edit that could affect…

원문 언어: 영어

trt-cpp-runtime-quickstart

Load and run a TensorRT engine (.plan / .engine) from C++ using the TensorRT 11 / 10.x **modern Runtime API**, avoiding the deprecated TRT 8.x binding-index APIs that older guidance still promotes. Use whenever the user asks about loading or running a…

원문 언어: 영어

trt-onnx-quickstart

Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime. Use when the user imports a non-LLM model to TensorRT, needs a verified engine from ONNX, hits trtexec "unsupported operator",…

원문 언어: 영어

trt-strong-typing-migration

Migrate a TensorRT build from weak typing (deprecated 10.12, removed 11.0) to strong typing — across Python INetworkDefinition builders, the trtexec CLI, and C++ builder code. Use when a TRT 11 upgrade breaks a weakly-typed build. Triggers: weakly typed to…

원문 언어: 영어

trt-torch-quickstart

Compile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default. Use when the user compiles PyTorch to TensorRT without ONNX, hits "enabled_precisions should not be used when use_explicit_typing=True", sees…

원문 언어: 영어