Repository Index

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

• inference
• high-preformance
• simd
• arm-neon

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

• nlp
• natural-language-processing
• natural-language-understanding
• language-model

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

• inference
• gpu
• machine-learning
• deep-learning

Hackable and optimized Transformers building blocks, supporting a composable construction.

Optimized primitives for collective multi-GPU communication

• communications
• cpp
• cuda
• deep-learning

Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.

• onednn
• oneapi
• performance
• cpp

CAI NEURAL API - Pascal based deep learning neural network API optimized for AVX, AVX2 and AVX512 instruction sets plus OpenCL capable devices including AMD, Intel and NVIDIA.

• pascal
• lazarus
• delphi
• free-pascal

🚀 Production-ready AI-friendly Go REST API boilerplate with Clean Architecture, JWT auth, RBAC, PostgreSQL migrations, and highly tested. AI-optimized with built-in guidelines for most used IDEs. Docker hot-reload, Swagger docs, one-command setup. Build production APIs in minutes, not weeks.

• api
• api-documentation
• authentication
• backend

OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. Designed for developers who need efficient audio transcription on mobile.

• asr
• conformer
• coreml
• ios