C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

⚠️DirectML is in maintenance mode ⚠️ DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tas…

huatuo是一个特性完整、零成本、高性能、低内存的近乎完美的Unity全平台原生c#热更方案。 Huatuo is a fully featured, zero-cost, high-performance, low-memory solution for Unity's all-platform native c# hotfix

ArcticDB is a high performance, serverless DataFrame database built for the Python Data Science ecosystem.

TinyML AI inference library

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

Explore fractals in an audio-visual sandbox

DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.

Samples and Tools for Windows ML.

The fastest RISC-V sandbox

gStore - a graph based RDF triple store.

Fast BPE

Antares: an automatic engine for multi-platform kernel generation and optimization. Supporting CPU, CUDA, ROCm, DirectX12, GraphCore, SYCL for CPU/GPU, OpenCL for AMD/NVIDIA, Android CPU/GPU backends.

Fork of TensorFlow accelerated by DirectML

The NVIDIA® Tools Extension SDK (NVTX) is a C-based Application Programming Interface (API) for annotating events, code ranges, and resources in your applications.

Intel® Video Processing Library (Intel® VPL) API, dispatcher, and examples

DirectML PluggableDevice plugin for TensorFlow 2

llama.cpp for Flutter

An implementation of HIP that works on CPUs, across OSes.

原XAPI2，清理了部分内容，仓库更简洁

Query-Adaptive Vector Search

Deepspeed windows information

A program that can render images as space filling curves.

Development has moved to SegmentLinking/cmssw

2D gravity simulation

Port of Facebook's LLaMA model in C/C++