torch-mlir
ncnn
| torch-mlir | ncnn | |
|---|---|---|
| 3 | 12 | |
| 1,186 | 19,275 | |
| 4.1% | 1.0% | |
| 9.8 | 9.4 | |
| 3 days ago | 3 days ago | |
| C++ | C++ | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
torch-mlir
-
Pytorch with AMD Radeon RX 6950 XT GPU: Is it possible on Windows 11?
You're best option is to use torchmlir : https://github.com/llvm/torch-mlir
- Abstract machine implementation for modern functional language.
-
Can julia be used in embedded devices replacing C?
The only real obstacle I see is what chris mentioned about some devices only having a C compiler...but then there's this: https://github.com/llvm/mlir-npcomp/blob/f339c258ba7d1d3798a84a614cca0ee622d2d2c6/docs/features.md
ncnn
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
ncnn uses Vulkan for GPU acceleration, I've seen it used in a few projects to get AMD hardware support.
https://github.com/Tencent/ncnn
-
[D] Best way to package Pytorch models as a standalone application
They're using NCNN to package the model. Have a look. https://github.com/Tencent/NCNN
-
Realtime object detection android app
Hi. Here is my prefered android app for realtime objet detection: https://github.com/nihui/ncnn-android-nanodet ; https://github.com/Tencent/ncnn contains a lot of android demo app for a lot of models.
- ncnn: High-performance neural network inference framework optimized for mobile
-
Esp32 tensorflow lite
ncnn home page: https://github.com/Tencent/ncnn
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
ncnn
-
Draw Things, Stable Diffusion in your pocket, 100% offline and free
Yes, Android devices tend to have bigger RAMs, making running 1024x1024 possible (this is not possible at all on iPhones, which could peak around 5GiB memory with my current implementation, some serious engineering required to bring that down on iPhone devices). The problem is I am not sure about speed. I would likely switch to NCNN (https://github.com/Tencent/ncnn) as the backend which have a decent Vulkan computing kernel support. It is definitely a possibility and there is a path to do that.
- What’s New in TensorFlow 2.10?
-
[Technical Article] OCR Upgrade
As the leading open-source inference framework in China and in the world, what we like are its almost zero cost cross-platform capability, high inference speed, and minimal deployment volume. (Project address: https://github.com/Tencent/ncnn)
-
Is there a functioning neural netowork or backbone written in pure C language only?
If you’re not planning on training the neural net on an embedded device and just do inference, this might interest you: https://github.com/Tencent/ncnn
What are some alternatives?
iree - A retargetable MLIR-based machine learning compiler and runtime toolkit.
XNNPACK - High-efficiency floating-point neural network inference operators for mobile, server, and Web
mlir-aie - An MLIR-based toolchain for AMD AI Engine-enabled devices.
rife-ncnn-vulkan - RIFE, Real-Time Intermediate Flow Estimation for Video Frame Interpolation implemented with ncnn library
circt - Circuit IR Compilers and Tools
deepdetect - Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
HVM - A massively parallel, optimal functional runtime in Rust
netron - Visualizer for neural network, deep learning and machine learning models
V8 - The official mirror of the V8 Git repository
darknet - Convolutional Neural Networks
coalton - Coalton is an efficient, statically typed functional programming language that supercharges Common Lisp.
RPi_64-bit_Zero-2-image - Raspberry Pi Zero 2 W 64-bit OS image with OpenCV, TensorFlow Lite and ncnn Framework.