Find where a TensorRT engine's output starts to disagree with its reference, by bisecting the pipeline to the first divergent boundary. Use when a TRT result differs from ONNX Runtime, PyTorch or a saved golden output. Triggers: TensorRT output is wrong,…
NVIDIA/trt-samples-for-hackathon-cn
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 3
- GitHub stars
- 1,677
- GitHub forks
- 350
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/NVIDIA/trt-samples-for-hackathon-cn.Loading the repository README…
Skills in this repository
classification pending
Showing 3 of 3 collected skills.
skill
occupation
description
updated
occupation
unclassified
description
updated
occupation
unclassified
description
Validate and analyze TensorRT performance data from paired layer-info JSON and profile/latency JSON files. Use when asked to inspect TensorRT, TRT, torch-tensorrt, or ONNX-TensorRT perf reports, verify that layer/profile JSON files are valid and from the same…
updated
occupation
unclassified
description
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…
updated
Showing 3 of 3 collected skills.