ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

These details have not been verified by PyPI

Project links

Homepage

Project description

ncnn

ncnn is a high-performance neural network inference framework optimized for mobile, embedded, and desktop deployment. It has no third-party runtime dependencies, runs across CPU and Vulkan GPU backends, and provides tools such as pnnx for converting PyTorch and ONNX models to ncnn. Developers can deploy deep learning models efficiently on phones, PCs, browsers, and edge devices. ncnn is currently being used in many Tencent applications, such as QQ, Qzone, WeChat, Pitu, and so on.

ncnn 是一个面向移动端、嵌入式和桌面端部署优化的高性能神经网络推理框架。 ncnn 无第三方运行时依赖，支持 CPU 和 Vulkan GPU 后端，并提供 pnnx 等工具将 PyTorch 和 ONNX 模型转换为 ncnn 模型。基于 ncnn，开发者可以将深度学习模型高效部署到手机、PC、浏览器和边缘设备上。 ncnn 目前已在腾讯多款应用中使用，如：QQ，Qzone，微信，天天 P 图等。

Quick Start

The recommended beginner path is PyTorch -> pnnx -> ncnn.

Install pnnx in a PyTorch environment

pip3 install pnnx

Export a PyTorch model to ncnn

import torch
import torch.nn as nn
import pnnx

class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 8, 1)
        self.relu = nn.ReLU()
        self.fc = nn.Linear(8, 4)

    def forward(self, x):
        x = self.conv(x)
        x = self.relu(x)
        x = x.mean((2, 3))
        return self.fc(x)

model = Model().eval()

x = torch.rand(1, 3, 224, 224)
pnnx.export(model, "model.pt", (x,))

This generates model.ncnn.param and model.ncnn.bin.

Run with ncnn C++ API

#include "net.h"

ncnn::Net net;
net.load_param("model.ncnn.param");
net.load_model("model.ncnn.bin");

ncnn::Mat in(224, 224, 3);

auto ex = net.create_extractor();
ex.input("in0", in);

ncnn::Mat out;
ex.extract("out0", out);

Or use Python

import numpy as np
import ncnn

net = ncnn.Net()
net.load_param("model.ncnn.param")
net.load_model("model.ncnn.bin")

x = np.zeros((3, 224, 224), np.float32)
mat = ncnn.Mat(x)

ex = net.create_extractor()
ex.input("in0", mat)

ret, out = ex.extract("out0")
print(np.array(out).shape)

See pnnx, use ncnn with PyTorch or ONNX, Python API, and examples for complete workflows.

Community

技术交流 QQ 群 637093648 (超多大佬) 答案：卷卷卷卷卷（已满）	Telegram Group https://t.me/ncnnyes	Discord Channel https://discord.gg/YRsxgmF
Pocky QQ 群（MLIR YES!） 677104663 (超多大佬) 答案：multi-level intermediate representation
他们都不知道 pnnx 有多好用群 818998520 (新群！)

Download & Build status

https://github.com/Tencent/ncnn/releases/latest

	how to build ncnn library on Linux / Windows / macOS / Raspberry Pi3, Pi4 / POWER / Android / NVIDIA Jetson / iOS / WebAssembly / AllWinner D1 / Loongson 2K1000
	Source
	Build for Android Build for Termux on Android
	Android
	Android shared
	Build for HarmonyOS with cross-compiling
	HarmonyOS
	HarmonyOS shared
	Build for iOS on macOS with xcode
	iOS
	iOS-Simulator
	Build for macOS
	macOS
	Mac-Catalyst
	watchOS
	watchOS-Simulator
	tvOS
	tvOS-Simulator
	visionOS
	visionOS-Simulator
	Apple xcframework
	Build for Linux / NVIDIA Jetson / Raspberry Pi3, Pi4 / POWER
	Ubuntu 22.04
	Ubuntu 24.04
	Build for Windows x64 using VS2017 Build for Windows x64 using MinGW-w64
	VS2015
	VS2017
	VS2019
	VS2022
	Build for WebAssembly
	WebAssembly
	Build for ARM Cortex-A family with cross-compiling Build for Hisilicon platform with cross-compiling Build for AllWinner D1 Build for Loongson 2K1000 Build for QNX
	Linux (arm)
	Linux (aarch64)
	Linux (mips)
	Linux (mips64)
	Linux (ppc64)
	Linux (riscv64)
	Linux (loongarch64)

Build

Use the prebuilt packages above when possible. To build from source, see the full how to build ncnn library guide for Linux, Windows, macOS, Android, iOS, WebAssembly, HarmonyOS, Raspberry Pi, Jetson, and embedded targets.

Common Linux build:

git clone --recursive https://github.com/Tencent/ncnn.git
cd ncnn
mkdir build && cd build
cmake -DCMAKE_BUILD_TYPE=Release -DNCNN_VULKAN=ON -DNCNN_BUILD_EXAMPLES=ON ..
cmake --build . -j$(nproc)

Model Conversion

Source model	Recommended path	Docs
PyTorch	`pnnx.export(model, "model.pt", (input_tensor,))` or `pnnx model.pt inputshape=[...]`	pnnx, PyTorch / ONNX guide
ONNX	`pnnx model.onnx`	pnnx, onnx tools
ncnn model optimization	`ncnnoptimize model.param model.bin new.param new.bin flag`	quantization, model file spec
Legacy Caffe / MXNet / Darknet	Use compatibility converters when maintaining older models	caffe, mxnet, darknet, AlexNet legacy tutorial

Use Netron to inspect .param, .onnx, and .pnnx.param graphs.

Features

No third-party runtime dependencies and no BLAS / NNPACK requirement.
Pure C++ implementation with C API and Python binding.
Optimized CPU inference for mobile and embedded processors, including ARM NEON and multi-core scheduling.
Vulkan GPU acceleration for supported platforms.
Low memory footprint with explicit blob/workspace allocator design.
Supports multi-input, multi-output, and multi-branch graphs.
PyTorch and ONNX conversion through pnnx, plus legacy converter support for older model formats.
Supports fp16 storage/arithmetic paths, int8 quantized inference, model optimization, and custom layers.
Direct memory reference loading for .param and .bin models.

Model and Workload Coverage

ncnn is still strong for classic and mobile CNN workloads, but current usage is broader than CNN-only deployment.

Classification and backbones: VGG, AlexNet, GoogleNet, Inception, ResNet, DenseNet, SENet, SqueezeNet, MobileNet, ShuffleNet, MNasNet.
Detection and face: SSD, Faster R-CNN, R-FCN, MTCNN, RetinaFace, scrfd, YOLOv2, YOLOv3, YOLOv4, YOLOv5, YOLOv7, YOLOv8, YOLOX, NanoDet.
Segmentation, pose, and OCR: FCN, PSPNet, UNet, YOLACT, SimplePose, PP-OCR examples.
Audio, generation, and language workloads are represented by community projects and examples where the model operators are supported.

For operator-level detail, see supported PyTorch operator status, supported ONNX operator status, and operation param weight table.

Project Examples

Area	Project
Image generation	zimage-ncnn-vulkan - Z-Image generation with ncnn and Vulkan
LLM / embedding / vision-language	ncnn_llm - LLM, embedding, and vision-language examples with ncnn
Android classification	ncnn-android-squeezenet
Android style transfer	ncnn-android-styletransfer
Android detection	ncnn-android-mobilenetssd, ncnn-android-yolov5, ncnn-android-yolov7, ncnn-android-scrfd
Face detection	mtcnn_ncnn
Qt / Android integration	qt_android_ncnn_lib_encrypt_example
Colorization	ncnn-colorization-siggraph17
Fortran binding	ncnn-fortran
Speech recognition	sherpa - real-time speech recognition on embedded and mobile devices

Documentation And FAQ

Topic	Links
Build	how to build
PyTorch / ONNX conversion	use ncnn with PyTorch or ONNX, pnnx, PyTorch converter notes
API and examples	C++ examples, Python API, low-level operation API
Model format	param and model file spec, operation param weight table
Extension	custom layer guide, plugin tools
FAQ	deepwiki, throw error, wrong result, Vulkan
Legacy beginner material	use ncnn with AlexNet, AlexNet Chinese tutorial

License

BSD 3 Clause

Project details

These details have not been verified by PyPI

Project links

Homepage

Release history Release notifications | RSS feed

This version

1.0.20260526

May 26, 2026

1.0.20260114

Jan 14, 2026

1.0.20250916

Sep 16, 2025

1.0.20250503

May 3, 2025

1.0.20250428

Apr 28, 2025

1.0.20241226

Dec 26, 2024

1.0.20240820

Aug 20, 2024

1.0.20240410

Apr 10, 2024

1.0.20240102

Jan 2, 2024

1.0.20231027

Oct 27, 2023

1.0.20230816

Aug 16, 2023

1.0.20230517

May 17, 2023

1.0.20230223

Feb 23, 2023

1.0.20221128

Nov 28, 2022

1.0.20220729

Jul 29, 2022

1.0.20220721

Jul 21, 2022

1.0.20220701

Jul 1, 2022

1.0.20220420

Apr 20, 2022

1.0.20220419

Apr 19, 2022

1.0.20220216

Feb 16, 2022

1.0.20211208

Dec 8, 2021

1.0.20210720

Jul 20, 2021

1.0.20210525

May 25, 2021

1.0.2023.2.23

Feb 23, 2023

1.0.2022.11.28

Nov 28, 2022

1.0.2022.7.29

Jul 29, 2022

1.0.2022.7.21

Jul 21, 2022

1.0.2022.7.1

Jul 1, 2022

1.0.2022.4.20

Apr 20, 2022

1.0.2022.4.19

Apr 19, 2022

1.0.2022.2.16

Feb 16, 2022

1.0.2021.12.8

Dec 8, 2021

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ncnn-1.0.20260526.tar.gz (4.7 MB view details)

Uploaded May 26, 2026 Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

ncnn-1.0.20260526-pp311-pypy311_pp73-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 PyPyWindows x86-64

ncnn-1.0.20260526-pp311-pypy311_pp73-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 PyPymanylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-pp311-pypy311_pp73-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 PyPymanylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-pp311-pypy311_pp73-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 PyPymanylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp314-cp314-win_arm64.whl (2.7 MB view details)

Uploaded May 26, 2026 CPython 3.14Windows ARM64

ncnn-1.0.20260526-cp314-cp314-win_amd64.whl (5.2 MB view details)

Uploaded May 26, 2026 CPython 3.14Windows x86-64

ncnn-1.0.20260526-cp314-cp314-win32.whl (4.4 MB view details)

Uploaded May 26, 2026 CPython 3.14Windows x86

ncnn-1.0.20260526-cp314-cp314-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.14musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp314-cp314-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.14musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp314-cp314-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.14musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp314-cp314-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.14musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp314-cp314-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.14musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp314-cp314-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.14manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp314-cp314-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.14manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.14manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp314-cp314-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.14manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.14manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp314-cp314-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.14macOS 11.0+ x86-64

ncnn-1.0.20260526-cp314-cp314-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.14macOS 11.0+ ARM64

ncnn-1.0.20260526-cp313-cp313-win_arm64.whl (2.6 MB view details)

Uploaded May 26, 2026 CPython 3.13Windows ARM64

ncnn-1.0.20260526-cp313-cp313-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.13Windows x86-64

ncnn-1.0.20260526-cp313-cp313-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.13Windows x86

ncnn-1.0.20260526-cp313-cp313-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.13musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp313-cp313-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.13musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp313-cp313-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.13musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp313-cp313-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.13musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp313-cp313-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.13musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp313-cp313-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.13manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp313-cp313-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.13manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.13manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp313-cp313-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.13manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.13manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp313-cp313-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.13macOS 11.0+ x86-64

ncnn-1.0.20260526-cp313-cp313-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.13macOS 11.0+ ARM64

ncnn-1.0.20260526-cp312-cp312-win_arm64.whl (2.6 MB view details)

Uploaded May 26, 2026 CPython 3.12Windows ARM64

ncnn-1.0.20260526-cp312-cp312-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.12Windows x86-64

ncnn-1.0.20260526-cp312-cp312-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.12Windows x86

ncnn-1.0.20260526-cp312-cp312-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.12musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp312-cp312-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.12musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp312-cp312-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.12musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp312-cp312-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.12musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp312-cp312-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.12musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp312-cp312-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.12manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp312-cp312-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.12manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.12manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp312-cp312-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.12manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.12manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp312-cp312-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.12macOS 11.0+ x86-64

ncnn-1.0.20260526-cp312-cp312-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.12macOS 11.0+ ARM64

ncnn-1.0.20260526-cp311-cp311-win_arm64.whl (2.6 MB view details)

Uploaded May 26, 2026 CPython 3.11Windows ARM64

ncnn-1.0.20260526-cp311-cp311-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.11Windows x86-64

ncnn-1.0.20260526-cp311-cp311-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.11Windows x86

ncnn-1.0.20260526-cp311-cp311-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.11musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp311-cp311-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.11musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp311-cp311-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.11musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp311-cp311-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.11musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp311-cp311-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.11musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp311-cp311-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.11manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp311-cp311-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.11manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.11manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp311-cp311-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.11manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.11manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp311-cp311-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.11macOS 11.0+ x86-64

ncnn-1.0.20260526-cp311-cp311-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.11macOS 11.0+ ARM64

ncnn-1.0.20260526-cp310-cp310-win_arm64.whl (2.6 MB view details)

Uploaded May 26, 2026 CPython 3.10Windows ARM64

ncnn-1.0.20260526-cp310-cp310-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.10Windows x86-64

ncnn-1.0.20260526-cp310-cp310-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.10Windows x86

ncnn-1.0.20260526-cp310-cp310-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.10musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp310-cp310-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.10musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp310-cp310-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.10musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp310-cp310-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.10musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp310-cp310-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.10musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp310-cp310-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.10manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp310-cp310-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.10manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.10manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp310-cp310-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.10manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.10manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp310-cp310-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.10macOS 11.0+ x86-64

ncnn-1.0.20260526-cp310-cp310-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.10macOS 11.0+ ARM64

ncnn-1.0.20260526-cp39-cp39-win_arm64.whl (2.6 MB view details)

Uploaded May 26, 2026 CPython 3.9Windows ARM64

ncnn-1.0.20260526-cp39-cp39-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.9Windows x86-64

ncnn-1.0.20260526-cp39-cp39-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.9Windows x86

ncnn-1.0.20260526-cp39-cp39-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.9musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp39-cp39-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.9musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp39-cp39-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.9musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp39-cp39-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.9musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp39-cp39-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.9musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp39-cp39-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.9manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp39-cp39-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.9manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.9manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp39-cp39-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.9manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp39-cp39-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.9manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp39-cp39-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.9macOS 11.0+ x86-64

ncnn-1.0.20260526-cp39-cp39-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.9macOS 11.0+ ARM64

ncnn-1.0.20260526-cp38-cp38-win_amd64.whl (5.1 MB view details)

Uploaded May 26, 2026 CPython 3.8Windows x86-64

ncnn-1.0.20260526-cp38-cp38-win32.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.8Windows x86

ncnn-1.0.20260526-cp38-cp38-musllinux_1_2_x86_64.whl (9.6 MB view details)

Uploaded May 26, 2026 CPython 3.8musllinux: musl 1.2+ x86-64

ncnn-1.0.20260526-cp38-cp38-musllinux_1_2_riscv64.whl (4.2 MB view details)

Uploaded May 26, 2026 CPython 3.8musllinux: musl 1.2+ riscv64

ncnn-1.0.20260526-cp38-cp38-musllinux_1_2_i686.whl (9.3 MB view details)

Uploaded May 26, 2026 CPython 3.8musllinux: musl 1.2+ i686

ncnn-1.0.20260526-cp38-cp38-musllinux_1_2_armv7l.whl (4.0 MB view details)

Uploaded May 26, 2026 CPython 3.8musllinux: musl 1.2+ ARMv7l

ncnn-1.0.20260526-cp38-cp38-musllinux_1_2_aarch64.whl (5.4 MB view details)

Uploaded May 26, 2026 CPython 3.8musllinux: musl 1.2+ ARM64

ncnn-1.0.20260526-cp38-cp38-manylinux_2_39_riscv64.whl (2.9 MB view details)

Uploaded May 26, 2026 CPython 3.8manylinux: glibc 2.39+ riscv64

ncnn-1.0.20260526-cp38-cp38-manylinux_2_31_armv7l.whl (3.0 MB view details)

Uploaded May 26, 2026 CPython 3.8manylinux: glibc 2.31+ ARMv7l

ncnn-1.0.20260526-cp38-cp38-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (8.4 MB view details)

Uploaded May 26, 2026 CPython 3.8manylinux: glibc 2.24+ x86-64manylinux: glibc 2.28+ x86-64

ncnn-1.0.20260526-cp38-cp38-manylinux_2_24_i686.manylinux_2_28_i686.whl (8.0 MB view details)

Uploaded May 26, 2026 CPython 3.8manylinux: glibc 2.24+ i686manylinux: glibc 2.28+ i686

ncnn-1.0.20260526-cp38-cp38-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl (4.3 MB view details)

Uploaded May 26, 2026 CPython 3.8manylinux: glibc 2.24+ ARM64manylinux: glibc 2.28+ ARM64

ncnn-1.0.20260526-cp38-cp38-macosx_11_0_x86_64.whl (10.7 MB view details)

Uploaded May 26, 2026 CPython 3.8macOS 11.0+ x86-64

ncnn-1.0.20260526-cp38-cp38-macosx_11_0_arm64.whl (6.4 MB view details)

Uploaded May 26, 2026 CPython 3.8macOS 11.0+ ARM64

File details

Details for the file ncnn-1.0.20260526.tar.gz.

File metadata

Download URL: ncnn-1.0.20260526.tar.gz
Upload date: May 26, 2026
Size: 4.7 MB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for ncnn-1.0.20260526.tar.gz
Algorithm	Hash digest
SHA256	`282f0f4a1beec1f5212aa0d22c00737418645055f33c2d2082922931cdbdc537`
MD5	`8cae96ed1a577e8bcf291f148a549291`
BLAKE2b-256	`5b77d6acfd9b652463a2037a1113954f2cf0aa7d4c414de31b01aeb1fd9bf9e7`

Algorithm	Hash digest
SHA256	`68c5cb2b7b645fcee404fc7e0b248f690218f464781d512ac19923036911eb30`
MD5	`0c7f5b1fa9cc54e8c2a1d12c691a4bbc`
BLAKE2b-256	`ed91a04fd4ea199906974388d977bcb6ff6eb238c53f4e5c2300e9731c7dab51`

Algorithm	Hash digest
SHA256	`e06d38bd14526914a255202d663cc03c3fa466629f51723f092cf13714c90be7`
MD5	`040c54b4e92c34af3a42bcb9b0933279`
BLAKE2b-256	`61943fb8918d46c8dfff573f39569d74be7f2d68012884ee4efb5b504dfe1051`

Algorithm	Hash digest
SHA256	`d9add20ddc55d341e0428c8462cfc965154f9ad823d700b31548ec68f4d12c13`
MD5	`f18c7d35d1412f364cc4acf5eae78e15`
BLAKE2b-256	`a44714bc248e2edf8a472fbbaf29f3540d548a983ba8963a39b22ff6c54da8ef`

Algorithm	Hash digest
SHA256	`5b25bf06c421364e7b773906dbccd10c479a9780a5b46c581df3a76957f7ea46`
MD5	`d97059385885208e401e471d7c0dff47`
BLAKE2b-256	`59babd9c70a72e90cde396f0aa5d6eba066ae6d0e6d11ab2c82928109b28d0c7`

Algorithm	Hash digest
SHA256	`572c5ff7c29a6c76d506e6937f2fc82b3fe8e4eb6673acf5f32305cb6dc03805`
MD5	`5393f5e7b43e84c2dafcc0a0462404bb`
BLAKE2b-256	`500e1f31a08ee1bf99f2ec4d393da7071336deafb52a508c6c5aa7a330999d5b`

Algorithm	Hash digest
SHA256	`a0095360167be4f6c0976dd08cc3215b4d4709432e3b411bda5713196d7e9ac5`
MD5	`448e3e8b1c7e6197428cdbc6d563c609`
BLAKE2b-256	`7a642766a568e0ce56866f925d6f3513a06da1202f6125d88a157d4a8c4ed79e`

Algorithm	Hash digest
SHA256	`6e1c0ba7d43ee203d689e581aef5a47086ff929ad4ad4f4d5dec8d6cbae8240e`
MD5	`30ee3fbf8b15009295e655bd3e090c4f`
BLAKE2b-256	`fbad3e60aea2bb5087428680a95c6e382dbb581f74cd6a22f96b567ff11b8efc`

Algorithm	Hash digest
SHA256	`f33acc5225709eb28408ad4e585eb9dca357d89ef4e84d0dd43062932ccfdabc`
MD5	`0673c5849eab644a01e4865bd496b53f`
BLAKE2b-256	`86200f1d5ead2b2558dd743ffb43a893d1b569313b7136a36c48f748e90f234f`

Algorithm	Hash digest
SHA256	`2337462401ab537f8bad13b51fde39b6c8df239e67b076fadb35ef2a5b327cde`
MD5	`468be50bca4bc4a5e3e42c966996be8b`
BLAKE2b-256	`696ee1c4a6dc91d28676473ecdc09b55d7f1945e3c07f57287a89eb26d679283`

Algorithm	Hash digest
SHA256	`fb61c4e1f059059e293cc0bc1e83bcc27443df90a49790dc30669c3666ed1b34`
MD5	`5a91f5b68bffdca45d73e4ba22ef8bf5`
BLAKE2b-256	`3d58583befdfc63602b0f1dc07cab779a54c7fc506e9af29c2e7c742c4b9f3ce`

Algorithm	Hash digest
SHA256	`9b58ff4c47710534491386ecc546a9d4b90f4483d348b0cdf81a1a503d24ba4b`
MD5	`a3082e992a7223478924fceee4e71f51`
BLAKE2b-256	`c4dbefaeb7ef25446fb32dbf69fc9dbb2b5d02d6be14d1580c8098ffebcce34c`

Algorithm	Hash digest
SHA256	`4f8f6bfe9df7a3069292f5379170e6ec4499846c15aa1bf4e5b89a297b3063fd`
MD5	`d16cdff11a21c32d3de58166eaf58e3a`
BLAKE2b-256	`2606f21ada086a991c2c14d586be766f7f9c099f7d2066025775c8bef28dfef0`

Algorithm	Hash digest
SHA256	`d3742cc9929bb3dc155107a459d8423086aebb7090fc201f960d59ac56ba0b4f`
MD5	`e28638be7162525488b848615ad7398b`
BLAKE2b-256	`368e0b0c404acb00628dc8fb5240f6215d16d0fb8b954296b1a0c5b783903d48`

Algorithm	Hash digest
SHA256	`f69ff04268ba6899081c80e9e2311c5169a270e0a76f8b39d546eea8b79e7057`
MD5	`387afcf5930299a36648efcf6e3edd90`
BLAKE2b-256	`10d58f8b80e2090aed6d5f764c81f35d3d81dfaa0942ab55093c68ac806d2bbe`

Algorithm	Hash digest
SHA256	`7bd5d62eeec025c65673757f6d11748629e9cada4b7e83da111a2cc2ae72afc0`
MD5	`adcdd6c1284809bcdc067e18e991e7d1`
BLAKE2b-256	`7c529c9d1fbd5d2e1006b0121d69620f7564fa5a1a799afdb5556fcfb8b31a3a`

Algorithm	Hash digest
SHA256	`dd0e4a8a2862a596bdfae71a8d9a4c3f729d03d6f590853365e54caf24c5ae7c`
MD5	`f6fa76e40d6917506c2ac1174dfde68f`
BLAKE2b-256	`d488c2f6b013c28b27deada40756757190a30840072c84db501c1ba41bd63616`

Algorithm	Hash digest
SHA256	`7f25a67921657f4014f37175bd9829a78cb8f58202e034d14941a255c00c0c15`
MD5	`f6bd382ac170c33475bfc410bd749f18`
BLAKE2b-256	`f3963f426860119054a2c1d3793d223d6f3a29ba4957a117ad9d6b2dbff8091e`

Algorithm	Hash digest
SHA256	`3215d83d4e94665b6088d7fda5b85b2c775361fd0aef8694110246bfd7308a8e`
MD5	`247a4a8335f97d8c5b5861287ae176e2`
BLAKE2b-256	`b5dd5b8f10bf992c3a7ab320292c2d1d9fff80a35357be6c55d127844e7fe97c`

Algorithm	Hash digest
SHA256	`eeec7b2332f7b7c64b2d19d0582e868a751dc559fc012af6915cf921a654ed59`
MD5	`7cca716248fb038725bba06d9850ae7c`
BLAKE2b-256	`889b032f07ce6d76af06bfec7ee3aea9c32a84d39020692785562d16e8fa89b6`

Algorithm	Hash digest
SHA256	`c7841bdcad6509be98c81eb84b7f623422986c0f28e22d6dd73d32ed1e45da36`
MD5	`e396e743c250567b0df47bc03399ee5c`
BLAKE2b-256	`5f578bac277bf432179bcd572cc746a20bf2a95bc83f3cf9666d183b4a84d0d3`

ncnn 1.0.20260526

Navigation

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Project description

Quick Start

Community

Download & Build status

Build

Model Conversion

Features

Model and Workload Coverage

Project Examples

Documentation And FAQ

License

Project details

Verified details

Maintainers

Unverified details

Project links

Meta

Classifiers

Release history Release notifications | RSS feed

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

Algorithm	Hash digest
SHA256	`e72a84cfba14ad0cb119bbdb00f597b62066bddebd14aede6f0bfa66f876c225`
MD5	`476aa98a33d21010b47f15207b533ccc`
BLAKE2b-256	`cc288ed8cdcd002a0465fa5bfc7f04ec82225140a4b287069f20082b19ba95f2`

Algorithm	Hash digest
SHA256	`686ba623a614c7ccdbe8fd4cd758584476007a40a469c96d5fd6a2fc2fd55812`
MD5	`5f92f7b555e657e6dff41c0b3ac0e4f8`
BLAKE2b-256	`32547877372c7b0d889ebc9a76d42958a6d0eaefe08e75ee2382c88efa70aabd`

Algorithm	Hash digest
SHA256	`3f67500072d9d850228b23fcccb4e7facdc6a05a86df0b5d4120efe3dcf9f1f0`
MD5	`f1a14093f4e5b55cdbcba9bd9e7800cf`
BLAKE2b-256	`2d5a26b8249bda309c26721548c2ef354fecad82364e4a47826f69cdf1b23cb7`

Algorithm	Hash digest
SHA256	`a8eb6b23633fbc1ab85dd70a450caca2b022355eacc36449ced5811954e260f4`
MD5	`4baeb208012a916f6ea690412964e8fc`
BLAKE2b-256	`ef8bb9f7d91ffa629b016239157d74c16df9812bd86a36490a100baeb523cd30`

Algorithm	Hash digest
SHA256	`858bb74982acd42138825ceaaf45c2fc43a968ea513d12d59f67b55cdea12579`
MD5	`cd8893ba8150fc1ab76717d774db1825`
BLAKE2b-256	`dcc8e3491ea76e0ee38e6f9cd6795177cfd8eac7fb8c145638bb2196ae275e45`

Algorithm	Hash digest
SHA256	`3ed6e3695951f4d85686ca840b38f776f5ef11fb4a10152dabb4ce5b49a3de5e`
MD5	`71059f3158b24eeabf6d2851c69ad4b7`
BLAKE2b-256	`896feabb4da22e0c45ef619a6c36b0fc66fe9c6889b95a2fe53bd56aa9caea8b`

Algorithm	Hash digest
SHA256	`1a32fee910f6dd3cd979e06081290f1c26d010cfdfd541c2a95284feed111ccd`
MD5	`a429480b17757f5bcf517974d57c95ab`
BLAKE2b-256	`6587ee8155a58d99f07309fc2d83857747ef18d81ea57541659ac2b48a3351a5`

Algorithm	Hash digest
SHA256	`d91a08d515763ce11e3a2a76871ddc3bcf145ced2fdc224d4d8e378c7ab61c5a`
MD5	`844e0ac848f7eb32acd12f7ebd919b81`
BLAKE2b-256	`48acb95b6814d7172874ec34bdc301bc2b429e8eea200619555290dedddb59f4`

Algorithm	Hash digest
SHA256	`28c1e2a574b8f9bcbcc8c95de94d7814fb25b1a106f12dae3b7a8a4344d2db4b`
MD5	`4fbe24d4640d1b4c00eb6635432fcbd9`
BLAKE2b-256	`2f2f1a8f4c5d83213ac459865fbea4af7051ab63c5934fd2813cccfaf9bf6409`

Algorithm	Hash digest
SHA256	`2254364e2241c78af793512a75e91143d1fb479abfaf8330ea968b6c44568c2f`
MD5	`a4152a29c26ec8f2df1cf390b69db3f2`
BLAKE2b-256	`09a356465586cca82334808770039c4dc89fadbd91a0da1bf0a7778d63959aec`