SDK to use local models on web easy
- ai-model
- ai-models
- local-ai
- web-ai
Repository Index
47,133 repositories indexed
169–192 of 345 · Most stars
Playport runs Windows games, 64-bit and now 32-bit, on a stock, non-jailbroken iPhone. Install a game from your library onto the phone, pick up a controller and press Play. The game runs on the phone's own CPU and GPU: no PC, no cloud, no stream.
eBPF based always-on CPU/GPU profiler auto-discovering targets in Kubernetes and systemd, zero code changes or restarts needed!
Translated🎨 GPU accelerated image / video and camera filter library based on Metal. Support macOS & iOS. Image, video, and camera filter framework
Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android
- vulkan
- raytracing
- graphics-engine
- graphics-library
VexCL is a C++ vector expression template library for OpenCL/CUDA/OpenMP
- opencl
- cuda
- c-plus-plus
- gpgpu
ThunderGBM: Fast GBDTs and Random Forests on GPUs
🎮 A modern Web graphics engine for production 2D and 3D experiences.
Fast and lightweight DB Client made in Rust and GPUI.
- database
- dbclient
- developer-tools
- gpui
Numerical linear algebra software package
- linear-algebra
- hpc
- gpu-computing
- cuda
DiffSharp: Differentiable Functional Programming
- machine-learning
- tensor
- dotnet
- autodiff
Native x86-64 Windows loader for Bloodborne (CUSA03173) with native CPU execution, Win32 runtime, and shadPS4-based Vulkan GPU rendering. Based on deadinside28's bbport. Bring your own game dump, no game files are included.
- bloodborne
- native
- pc
- port
Anvil is a cross-platform framework for Vulkan
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf
webgpu.h - C version of the JS API, for both native and Wasm. A multi-vendor standard between Dawn/Emdawnwebgpu and wgpu-native. Designed primarily for binding into higher-level languages.
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
- apple-silicon
- audio-generation
- claude-code
- game-audio
WebGPU tutorials inspired by LearningWebGL.com. Use both WGSL and GLSL/SPIR-V.
- webgpu
- wgsl
Build 3D apps with React
A single-file zero-overhead C++ idiomatic wrapper for WebGPU native
Samsung Tizen root
- embedded-linux
- firmware-analysis
- hardware-hacking
- mali-gpu
Pure Go GUI toolkit built on GoGPU — widgets, layouts, styling
- go
- golang
- gui
- ui
A GPU implementation of Convolutional Neural Nets in C++
The New Official Aparapi: a framework for executing native Java and Scala code on the GPU.
- aparapi
- gpu
- opencl
- java
A blazingly fast programmatic video engine, made for agents.