ncnn is a high-performance neural network inference framework optimized for the mobile platform
Repository Index
111,821 visible repositories in the index
1–24 of 52 · Most stars
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
- mnn
- convolution
- vulkan
- embedded-devices
Kolmogorov Arnold Networks
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
- ai
- amd-gpu
- apple-silicon
- asr
一键将音视频转化为小红书/公众号/知识笔记/思维导图/视频字幕等各种风格的文档。
A retargetable MLIR-based machine learning compiler and runtime toolkit.
- mlir
- vulkan
- tensorflow
- spirv
One layout engine for JSX, HTML, and CSS. Render images, SVG, PDFs, or a paint tree. No headless browser.
- satori
- jsx
- og-image
- cloudflare-workers
Self-hosted AI audio transcription
Kandinsky 2 — multilingual text2image latent diffusion model
- image-generation
- text-to-image
- diffusion
- image2image
NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
- real-esrgan
- ncnn
- nvidia
- intel
Continuous Thought Machines, because thought takes time and reasoning is a process.
A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
- facial-expression-recognition
- face-recognition
- fer2013
- ckan-extension
Project page for End-to-end Recovery of Human Shape and Pose
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
- speech-synthesis
- neural-vocoder
- text-to-speech
- pytorch
Official repository of Evolutionary Optimization of Model Merging Recipes
Demo of in-browser Fast Neural Style Transfer with deeplearn.js library
Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
- fine-tuning
- hypernetworks
- llm
- lora
Multivariate imputation and matrix completion algorithms implemented in Python
A web-based application for quick, scalable, and automated hyperparameter tuning and stacked ensembling in Python.
- machine-learning
- ensemble-learning
- stacked-ensembles
- scikit-learn
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!