zhangxiangxiao

Xiang Zhang's starred repositories

emscripten

Emscripten: An LLVM-to-WebAssembly Compiler

Language:C++NOASSERTION25237 589 9029

pure

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

Language:JavaScriptNOASSERTION23431 731 580

squoosh

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

Language:TypeScriptApache-2.021110 239 595

vllm

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

Language:PythonApache-2.019928 192 2817

Skeleton

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

Language:CSSMIT19021 495 204

DocsGPT

GPT-powered chat for documentation, chat with your documents

Language:PythonMIT14274 87 341

faker

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

Language:TypeScriptNOASSERTION11918 36 646

channels

Developer-friendly asynchrony for Django

Language:PythonBSD-3-Clause5962 160 1256

tch-rs

Rust bindings for the C++ api of PyTorch.

Language:RustApache-2.03917 48 546

_hyperscript

a small scripting language for the web

Language:JavaScriptBSD-2-Clause2813 32 268

html-css-course

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

Language:HTML2339 77 14

daphne

Django Channels HTTP/WebSocket server

Language:PythonBSD-3-Clause2285 44 314

Pyrebase

A simple python wrapper for the Firebase API.

Language:Python2048 45 362

django-htmx

Extensions for using Django with htmx.

Language:JavaScriptMIT1431 39 68

LLMStack

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

Language:PythonNOASSERTION1163 18 37

patcher9x

Patch for Windows 9x to fix CPU issues

Language:CMIT654 25 23

OmniQuant

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

Language:PythonMIT594 16 64

softgpu

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

Language:CMIT582 17 77

webgpu-torch

Tensor computation with WebGPU acceleration

Language:TypeScriptMIT551 17 7

code-llama-for-vscode

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

Language:PythonMIT520 6 11

nestjs-starter

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

Language:TypeScript458 8 29

torch-js

Node.js binding for PyTorch.

Language:C++MIT292 6 4

wasm-gpt

Tensor library for machine learning

Language:CMIT275 80

typescript.el

TypeScript-support for Emacs

Language:Emacs LispGPL-3.0260 14 85

Genymotion_A11_libhoudini

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

MIT210 4 11

pytorch

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

Language:PythonNOASSERTION182 9 33

llava-cpp-server

LLaVA server (llama.cpp).

Language:C++MIT166 3 4

torch-js

Node.js binding for PyTorch.

Language:C++MIT1808

web-diffusion

Language:Vue900

pytorch-unified-memory

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Language:PythonNOASSERTION100