# Tencent/ncnn

> High-performance C++ neural network inference framework for deploying deep learning models on mobile, embedded and desktop devices, with CPU/Vulkan GPU backends and the pnnx converter for PyTorch and ONNX models.

- Magnitude: 0.8 out of 10 — Steady
- Stars: 23,935 total · +1 star measured 2026-10-11, 11:04–12:35 UTC, ≈ 2 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · Created: 2017-06-30 · Last push: 2026-10-10
- GitHub: https://github.com/Tencent/ncnn · Page: https://gitnova.dev/en/r/Tencent/ncnn

## Useful for

- Convert a PyTorch or ONNX model to ncnn with pnnx and run inference on an Android or iOS app
- Embed an int8-quantized CNN detector into an embedded edge device without third-party runtime deps
- Speed up CPU inference on ARM devices using NEON and multi-core scheduling

## Why it’s here

- Star-counter measurements on 2026-10-11 (UTC), 11:04–12:35: 23934 → 23935 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +2 stars, using observed gains and the previous day.
- GitHub Trending C++ today: #14, +1 star.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 4,522
- Issues and pull requests: 6,909
- Watchers: 569
- Average over the last week: 4 per day
- Usual pace: 5 per day
- Stars in the last hour (measured): 1
- Latest release: 20260526 (2026-05-26)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-12 … 2026-10-11: 4, 6, 5, 3, 3, 8, 9, 3, 5, 8, 11, 3, 3, 4, 4, 6, 11, 8, 8, 1, 2, 1, 2, 1, 5, 6, 7, 6, 2, 1

## Spotted in now

- GitHub Trending C++ today: #14, +1 star

## Similar by description

1. **microsoft/onnxruntime** — 1.8 · Steady · Language models · C++ · +0 stars measured 2026-10-11, 00:02–12:32 UTC, ≈ 2 by evening
   Cross-platform accelerator for ML inference and training. Runs models from PyTorch, TensorFlow, scikit-learn and others via the ONNX format with graph optimizations and hardware acceleration.
   Full card: https://gitnova.dev/en/r/microsoft/onnxruntime.md
2. **tracel-ai/burn** — 1.4 · Steady · Language models · Rust · +2 stars measured 2026-10-11, 00:01–12:33 UTC, ≈ 5 by evening
   A Rust tensor library and deep learning framework where training and inference share one codebase, with JIT compilation and autodiff. Runs on CUDA, ROCm, Metal, Vulkan, WebGPU and CPU.
   Full card: https://gitnova.dev/en/r/tracel-ai/burn.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-11 12:38 UTC, updated every 30 minutes.