# NVIDIA/trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

Repository: https://github.com/NVIDIA/trt-samples-for-hackathon-cn
Canonical: https://ross.abutalabs.com/products/trt-samples-for-hackathon-cn
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-21T14:15:58+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 62, longevity 100
- inputs: {"age_days": 1993, "days_push": 43, "days_rel": 43, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1666, forks 351 (observed 2026-08-28T04:05:19.133530+00:00)

## What it is
An NVIDIA-maintained tutorial repository for TensorRT beginners and developers, containing a 'cookbook' of rich code examples covering API usage, model building, plugin writing, and graph optimization, plus annual China TensorRT Hackathon materials. It also links to video tutorial slides and datasets.

## Use cases
- learn TensorRT from scratch with code examples
- build and run models with TensorRT native APIs or parsers
- write custom TensorRT plugins
- optimize computation graphs for GPU inference
- find reference implementations from TensorRT Hackathon competitions
- accelerate deep learning model inference on NVIDIA GPUs

## When to choose
- you are a beginner learning TensorRT inference optimization
- you need concrete code samples for TensorRT APIs, parsers, or plugin development
- you want hackathon reference implementations for optimizing classic models

## When to avoid
- you need a production inference serving framework rather than learning samples
- you use non-NVIDIA hardware or runtimes like ONNX Runtime or OpenVINO
- you need training frameworks rather than inference optimization

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, gpu-computing, developer-tools
- domain: deep-learning, gpu-computing, tutorials, developer-tools
- platform: python, cross-platform
- tags: tensorrt, nvidia, inference-optimization, hackathon, code-samples, cookbook, model-deployment, gpu, linux

## Member repositories
- NVIDIA/trt-samples-for-hackathon-cn (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:19.133530+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:42:57.060809+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/trt-samples-for-hackathon-cn (fetched 2026-08-28T04:05:19.133530+00:00, sha e440397739d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.