ncnn is a high-performance neural network inference framework optimized for the mobile platform
Repository Index
47,133 repositories indexed
1–22 of 22 · Most stars
High-performance In-browser LLM Inference Engine
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
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
- tensorrt
- nvidia
- deep-learning
- inference
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
- yolox
- yolov3
- onnx
- tensorrt
Build, Manage and Deploy AI/ML Systems
- machine-learning
- model-management
- ai
- ml
Multi-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary differential equations (ODEs), stochastic differential equations (SDEs), delay differential equations (DDEs), differential-algebraic equations (DAEs), and more in Julia.
- differential-equations
- differentialequations
- julia
- ode
TranslatedHigh-performance · Lightweight · AI Native Video workspace. A video creation workspace for the AI era. On the canvas, freely connect ideas and materials together with the Agent.
- ai-image-generation
- ai-video
- ai-video-generation
- ai-workspace
ILGPU JIT Compiler for high-performance .Net GPU programs
⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.
- go
- rule-engine
- edge-computing
- iot
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
- reinforcement-learning
- parallel-processing
- cpp17
- pybind11
Fast Clojure Matrix Library
🍇 GRAPE is a Rust/Python Graph Representation Learning library for Predictions and Evaluations
- graph
- high-performance
- machine-learning
- knowledge-graph
High-performance, time-indexed object storage for robotics and industrial IoT
- blob-storage
- storage-engine
- storage
- historian
High-performance Bayesian Data Analysis on the GPU in Clojure
- clojure
- bayesian-inference
- bayesian-data-analysis
- gpu-computing
CEED Library: Code for Efficient Extensible Discretizations
- ceed
- high-order
- exascale-computing
- api
Clojure library for CUDA development
- clojure-library
- clojure
- cuda-development
- cuda
High-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guarantees
Born is a modern ML framework for Go — train and deploy models as single binaries. Pure Go, zero CGO, GPU accelerated.
- autodiff
- automatic-differentiation
- cross-platform
- deep-learning
Ultra high-performance secp256k1 ECC engine | Python, Node.js, Rust, Go, C#, Swift, Java bindings | CUDA, Metal, OpenCL GPU | ECDSA, Schnorr, FROST, MuSig2, BIP-352 | 15+ platforms
- cryptography
- cuda
- riscv
- secp256k1