CUDA checkpoint and restore utility

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Patch for Windows 9x to fix CPU issues

SW and HW accelerated GPU driver for Windows 9x Virtual Machines

Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch

No-code multi-agent framework to build LLM Agents, workflows and applications with your data

A high-throughput and memory-efficient inference and serving engine for LLMs

LLaVA server (llama.cpp).

Genymotion ARM, ARMv7, ARMv8/ARM64 Translation for Android 11

Generate massive amounts of fake data in the browser and node.js

GPT-powered chat for documentation, chat with your documents

Tensor computation with WebGPU acceleration

Tensor library for machine learning

Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.

Make images smaller using best-in-class codecs, right in the browser.

Emscripten: An LLVM-to-WebAssembly Compiler

A simple python wrapper for the Firebase API.

Extensions for using Django with htmx.

Starter files, final projects, and FAQ for my HTML + CSS course

A set of small, responsive CSS modules that you can use in every web project.

Skeleton: A Dead Simple, Responsive Boilerplate for Mobile-Friendly Development

a small scripting language for the web

Developer-friendly asynchrony for Django

Django Channels HTTP/WebSocket server

Rust bindings for the C++ api of PyTorch.

Node.js binding for PyTorch.

Node.js binding for PyTorch.

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

NestJS MVC boilerplate for rapid development with battle-tested standards.